Numerical control machine tool adjusting method and device, electronic equipment and computer readable medium

Abstract

The embodiment of the invention discloses a numerical control machine tool adjusting method and device, electronic equipment and a computer readable medium. A specific embodiment of the method comprises the following steps: collecting initial machine tool data of a numerical control machine tool through an edge gateway; workpieces produced by the numerical control machine tool are detected, and workpiece detection data are obtained; binding the initial machine tool data with the workpiece detection data to obtain workpiece production quality data; based on the standard workpiece data information, performing production quality evaluation on the workpiece production quality data to obtain a dimensional deviation ratio and a cutting stability index; in response to the situation that the size deviation ratio and / or the cutting stability index do not reach the preset standard value, correspondingly machined appliance parameter data are searched in a preset technology knowledge base; converting the appliance parameter data into a machine tool execution instruction; and writing into a control system of the numerical control machine tool to process the workpiece. According to the implementation mode, the numerical control machine tool can adjust the parameters in real time according to the quality of the workpiece, and the machining quality and the yield of the workpiece are improved.

Description

Technical Field

[0001] The embodiments of this disclosure relate to the field of computer technology, and more specifically to CNC machine tool adjustment methods, apparatus, electronic devices, and computer-readable media. Background Technology

[0002] The settings parameters of CNC machine tools affect workpiece quality. Machine tool operating status data (e.g., spindle load, feed rate, vibration) and workpiece quality inspection data (e.g., dimensions, surface finish) are managed by different systems and departments, making effective correlation impossible. This hinders real-time control of workpiece quality and adjustment of the CNC machine tool. The typical method for adjusting CNC machine tools is manual operation of the machine tool control system to adjust parameters and issue programs.

[0003] However, when using the above method to adjust CNC machine tools, the following technical problems often occur: After a batch of workpieces is processed, it is sent to offline quality inspection equipment for testing. By the time quality defects are discovered, a large number of scrap products have already been produced, resulting in a waste of materials and labor time.

[0004] When quality issues arise, adjusting machining parameters (e.g., spindle speed, feed rate, tool compensation) relies on experienced engineers to identify and correct the problem. Real-time, automatic adjustments to CNC machine tools are not possible, resulting in slow response times and wasted machining materials.

[0005] The information disclosed in this background section is only intended to enhance the understanding of the background of the inventive concept, and therefore may contain information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0007] Some embodiments of this disclosure provide CNC machine tool adjustment methods, apparatuses, electronic devices, and computer-readable media to solve one or more of the technical problems mentioned in the background section above.

[0008] In a first aspect, some embodiments of this disclosure provide a CNC machine tool adjustment method, comprising: acquiring real-time data of the CNC machine tool through an edge gateway to obtain initial machine tool data; performing real-time detection on the workpiece produced by the CNC machine tool to obtain workpiece detection data; binding the initial machine tool data and the workpiece detection data to obtain workpiece production quality data; performing production quality evaluation on the workpiece production quality data based on standard workpiece data information to obtain dimensional deviation rate and cutting stability index; responding to the dimensional deviation rate being greater than a first preset standard value and / or the cutting stability index being less than a second preset standard value, searching for tool parameter data corresponding to the CNC machine tool in a preset process knowledge base; converting the tool parameter data into machine tool execution instructions; and writing the machine tool execution instructions into the control system of the CNC machine tool for workpiece processing.

[0009] Secondly, some embodiments of this disclosure provide a CNC machine tool adjustment device, comprising: a data acquisition unit configured to acquire real-time data of the CNC machine tool through an edge gateway to obtain initial machine tool data; a workpiece detection unit configured to perform real-time detection on the workpiece produced by the CNC machine tool to obtain workpiece detection data; a data binding unit configured to bind the initial machine tool data and the workpiece detection data to obtain workpiece production quality data; a quality assessment unit configured to perform production quality assessment on the workpiece production quality data based on standard workpiece data information to obtain a dimensional deviation rate and a cutting stability index; a parameter lookup unit configured to, in response to the dimensional deviation rate being greater than a first preset standard value and / or the cutting stability index being less than a second preset standard value, look up tool parameter data corresponding to the CNC machine tool in a preset process knowledge base; an instruction generation unit configured to convert the tool parameter data into machine tool execution instructions; and a machine tool control unit configured to write the machine tool execution instructions into the control system of the CNC machine tool for workpiece processing.

[0010] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, such that when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any implementation of the first aspect.

[0011] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method as described in any implementation of the first aspect.

[0012] The various embodiments of this disclosure have the following beneficial effects: Through the CNC machine tool adjustment methods of some embodiments of this disclosure, the CNC machine tool can adjust parameters in real time according to the quality of the workpiece, improving the machining quality and yield of the workpiece. Specifically, the reason for the low workpiece yield is that, due to post-production sampling inspection, when workpiece quality defects are discovered, the CNC machine tool has already produced unqualified workpieces, leading to serious material waste. Based on this, the CNC machine tool adjustment methods of some embodiments of this disclosure first collect real-time data of the CNC machine tool through an edge gateway to obtain initial machine tool data. This allows for real-time acquisition of data during the machining process, providing a data foundation for subsequent analysis. Second, the workpieces produced by the CNC machine tool are inspected in real time to obtain workpiece inspection data. This transforms quality control from offline sampling inspection to online inspection, achieving real-time quality supervision. Then, the initial machine tool data and the workpiece inspection data are bound together to obtain workpiece production quality data. This establishes a mapping relationship between the machining parameters of the CNC machine tool and the workpiece quality results, realizing full-process quality traceability. Next, based on standard workpiece data, the production quality data of the aforementioned workpiece is evaluated to obtain the dimensional deviation rate and cutting stability index. This achieves quantitative evaluation and real-time monitoring of the machining status, providing a decision-making basis for accurately adjusting the CNC machine tool. Subsequently, in response to the dimensional deviation rate exceeding a first preset standard value and / or the cutting stability index falling below a second preset standard value, the corresponding tool parameter data for machining on the CNC machine tool is retrieved from the preset process knowledge base. Thus, the optimization scheme is matched using the expert knowledge base, replacing the CNC machine tool adjustment mode that relies on manual experience. Then, the tool parameter data is converted into machine tool execution instructions. This achieves automatic conversion from optimization strategy to executable code. Finally, the machine tool execution instructions are written into the control system of the CNC machine tool for workpiece machining. This completes the closed-loop and automated control of the CNC machine tool from machining parameters to adjustment instructions, ensuring that the optimization strategy can be applied to the workpiece production process in real time. In summary, by adjusting and controlling CNC machine tools through real-time data acquisition, online quality inspection, data fusion analysis, intelligent decision-making, and automatic execution, the automatic adjustment of the CNC machine tool processing process and the stable improvement of workpiece quality are realized. Machine tool parameters can be controlled in real time according to the processing quality status, thereby improving workpiece processing quality, reducing the defect rate, and increasing production efficiency. Attached Figure Description

[0013] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0014] Figure 1This is a flowchart of some embodiments of the CNC machine tool adjustment method according to the present disclosure; Figure 2 This is a schematic diagram of the structure of some embodiments of the CNC machine tool adjustment device according to the present disclosure; Figure 3 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0015] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0016] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0017] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0018] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0019] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0020] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0021] refer to Figure 1 The diagram illustrates a flow 100 of some embodiments of a CNC machine tool adjustment method according to the present disclosure. This CNC machine tool adjustment method includes the following steps: Step 101: Collect real-time data of the CNC machine tool through the edge gateway to obtain initial machine tool data.

[0022] In some embodiments, the executing entity (e.g., an electronic device) of the above-described CNC machine tool adjustment method can be hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster composed of multiple servers or terminal devices, or as a single server or a single terminal device. When the computing device is software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules to provide distributed services, or as a single software or software module. No specific limitations are made here. The aforementioned edge gateway can be a hardware device deployed on the side of the CNC machine tool. The aforementioned real-time data can be various status parameters and operating information generated within the control system during the machining operation of the CNC machine tool. The aforementioned initial machine tool data can refer to the raw data directly collected from the CNC machine tool through the edge gateway and initially integrated. In a workpiece production scenario, the aforementioned edge gateway can perform preliminary processing on the raw data of the CNC machine tool and upload it to the upper-level management system. The aforementioned real-time data may include: axis data (e.g., actual position, commanded position, and following error of the X, Y, and Z axes), spindle data (e.g., actual spindle speed, commanded speed, load current, and temperature), feed rate (e.g., actual feed speed and programmed feed speed), alarm information (e.g., various fault and warning codes), tool information (e.g., current tool number and tool life count), and program information (e.g., the currently running program segment number).

[0023] In some optional implementations of certain embodiments, the aforementioned execution entity can collect real-time data from the CNC machine tool through an edge gateway to obtain initial machine tool data, which may include the following steps: The first step is to physically connect the aforementioned edge gateway to the control system of the CNC machine tool. This physical connection can be achieved by using actual cables to connect the edge gateway to the hardware interface of the CNC machine tool's control system. The control system of the CNC machine tool can be a system that controls all movements and logical operations of the machine tool. Examples include a CNC (Computer Numerical Control Unit) or a PLC (Programmable Logic Controller).

[0024] The second step involves configuring a communication protocol driver compatible with the control system in the edge gateway to establish a communication connection channel. This communication protocol driver can be a digital communication protocol for CNC machine tool data. For example, it could be the FOCAS protocol. The communication connection channel can be a virtual data transmission channel established between the edge gateway and the CNC machine tool control system.

[0025] The third step involves defining data acquisition tags in the edge gateway based on the data source addresses corresponding to the aforementioned communication connection channels, thus obtaining a data acquisition tag set. The aforementioned data source addresses can be the specific memory addresses where data is stored within the CNC machine tool control system. The aforementioned data acquisition tags can be identifiers defined for each data source address.

[0026] The fourth step involves collecting data from each data acquisition tag in the aforementioned data acquisition tag set, based on the data source address, to obtain a real-time dataset. This real-time dataset can be a collection of current values ​​of each data acquisition tag read from the CNC machine tool within the acquisition period.

[0027] The fifth step is to integrate the various real-time data points in the aforementioned real-time dataset to obtain the initial machine tool data. This integration may involve preprocessing the collected raw data. For example, this preprocessing could include data cleaning and format conversion (e.g., converting the format to JSON).

[0028] Step 102: Perform real-time inspection on the workpiece produced by the CNC machine tool to obtain workpiece inspection data.

[0029] In some embodiments, the aforementioned execution entity can perform real-time inspection of the workpiece produced by the CNC machine tool to obtain workpiece inspection data. This workpiece inspection data can be quantitative data describing various quality characteristics of the workpiece. For example, the thickness of a flat workpiece can be 5.01 mm. The surface scratch depth of the flat workpiece can be 0.02 mm. In practice, workpiece inspection is performed by deploying hardware devices (e.g., industrial cameras and edge computers).

[0030] In some optional implementations of certain embodiments, the execution entity can perform real-time detection on the workpiece produced by the CNC machine tool to obtain workpiece detection data, which may include the following steps: The first step is to deploy online inspection equipment in the machining area of ​​the CNC machine tool. This online inspection equipment can be a device that automatically measures the workpiece within the production line. The machining area can be the physical space where the CNC machine tool performs cutting operations or an area adjacent to its exit. For example, the machining area can be the exit of a production conveyor belt.

[0031] The second step involves collecting the workpiece's quality characteristic data in real time through the online inspection equipment upon completion of the workpiece processing. This quality characteristic data can be raw measured values ​​describing specific quality attributes of the workpiece. In a workpiece production scenario, this quality characteristic data may include: dimensional features, geometric tolerances, surface features, and surface defects.

[0032] The third step is to associate the aforementioned quality characteristic data with the unique identification information of the aforementioned workpiece to obtain the workpiece inspection data. The aforementioned unique identification information can be an identifier that uniquely distinguishes a single workpiece (e.g., a serial number, barcode, or QR code).

[0033] Step 103: Bind the initial machine tool data and workpiece inspection data to obtain workpiece production quality data.

[0034] In some embodiments, the executing entity can bind the initial machine tool data and the workpiece inspection data to obtain workpiece production quality data. The workpiece production quality data can be data that binds CNC machine tool data with the quality data of the produced workpiece.

[0035] As an example, firstly, an index (e.g., a unique identifier) ​​can be extracted from the workpiece inspection data for association. Then, the workpiece is identified by the index, along with the initial machine tool data, and associated to obtain the workpiece production quality data.

[0036] In some optional implementations of certain embodiments, the execution entity can bind the initial machine tool data and the workpiece inspection data to obtain workpiece production quality data, which may include the following steps: The first step is to extract the unique identification information and inspection timestamp from the aforementioned workpiece inspection data. The unique identification information can be an identifier used to distinguish the identity of an individual workpiece (e.g., a serial number). The inspection timestamp can be information recording the time the workpiece was inspected.

[0037] The second step involves matching the CNC machine tool operating parameter data corresponding to the time window from the initial machine tool data, based on the aforementioned detection timestamp. For example, in a workpiece generation scenario, the aforementioned CNC machine tool operating parameter data could be a real-time spindle speed of 3200 RPM and a tool wear of 0.012 mm. The aforementioned time window can be the time range corresponding to the workpiece detection, ending at the detection timestamp. The aforementioned CNC machine tool operating parameter data can be the detailed behavioral data of the machine tool during the machining of the workpiece within the time window, as found in the initial machine tool data.

[0038] The third step is to establish a data mapping relationship between the aforementioned workpiece unique identification information, the aforementioned CNC machine tool operating parameter data, and the aforementioned workpiece inspection data. This data mapping relationship can be a programmed pointer that associates the workpiece unique identification information, the CNC machine tool operating parameter data, and the workpiece inspection data. This pointer can connect the three sets of data (workpiece unique identification information, CNC machine tool operating parameter data, and workpiece inspection data).

[0039] The fourth step is to perform structured encapsulation of the above data mapping relationship to obtain workpiece production quality data. This structured encapsulation can be a step of standardizing the corresponding data in the data mapping relationship. In practice, the data corresponding to the data mapping relationship (workpiece unique identifier information, CNC machine tool operating parameter data, and workpiece inspection data) can be processed into JSON to obtain JSON type data.

[0040] Step 104: Based on standard workpiece data, evaluate the production quality of the workpiece to obtain the dimensional deviation rate and cutting stability index.

[0041] In some embodiments, the aforementioned execution entity can perform a production quality assessment on the aforementioned workpiece production quality data based on standard workpiece data information to obtain a dimensional deviation rate and a cutting stability index. The dimensional deviation rate can be an index used to determine the deviation rate between the dimensions of the produced workpiece and the dimensions of a standard workpiece. The cutting stability index can be an index used to determine the stability of the CNC machine tool's operation during the production process. The aforementioned standard workpiece data information can be workpiece reference data conforming to design standards. In the workpiece production scenario, the lower the dimensional deviation rate, the closer the overall dimensions of the workpiece are to the standard workpiece. The higher the cutting stability index, the more stable the CNC machine tool is during the cutting process. The aforementioned workpiece reference data can include: design values ​​for various dimensions of the workpiece (e.g., length, diameter, and hole diameter); and weight values ​​for each dimension of the workpiece (the degree of influence of the dimension on the workpiece's function, assigned different weights). For example, the weight of the journal diameter that directly mates with the inner ring of the bearing can be 0.4.

[0042] As an example, the aforementioned dimensional deviation rate can be generated using the following steps: First, the measured values ​​of each key dimension can be extracted from the workpiece production quality data to form an actual value list. Second, the standard values ​​of each key dimension can be extracted from the standard workpiece data to form a standard value list. Then, the deviation value of a single dimension is determined using the data from both the actual value list and the standard value list. Finally, the weights corresponding to each key dimension in the standard workpiece data are used to weight and sum the obtained deviation values ​​to obtain the dimensional deviation rate.

[0043] As an example, the aforementioned cutting stability index can be generated using the following steps: First, the spindle load sequence, feed rate sequence, and vibration amplitude sequence can be extracted from the workpiece production quality data according to the workpiece production time window. Second, the standard deviation and mean of the spindle load sequence are determined, and the load fluctuation rate is obtained using the ratio of the standard deviation to the mean. Then, the mean of the feed rate sequence and the standard value of the feed rate in the standard workpiece data are determined, and the ratio of the mean to the standard value is obtained, resulting in the speed deviation ratio. Next, the vibration amplitudes exceeding the safety threshold in the vibration amplitude sequence are normalized to obtain the amplitude overclocking frequency. Finally, the values ​​of each indicator (load fluctuation rate, speed deviation ratio, and amplitude overclocking frequency) in the standard workpiece data are weighted and summed to obtain the cutting stability index.

[0044] In some optional implementations of certain embodiments, the execution entity may evaluate the processing status of the workpiece production quality data based on standard workpiece data information to obtain dimensional deviation rate and cutting stability index, which may include the following steps: The first step is to extract the measured dimension set data and the workpiece inspection timestamp from the aforementioned workpiece production quality data. The measured dimension set data refers to the actual measured values ​​of each key dimension from the workpiece production quality data. The workpiece inspection timestamp can be the time point when the workpiece underwent quality inspection. In the workpiece production scenario, the measured dimension set data could be "diameter: 20.01, length: 105.2, height: 50.15". In practice, firstly, the JSON structure of the workpiece production quality data can be parsed. Then, the fields corresponding to the actual measured values ​​and timestamps of each key dimension are extracted to obtain the numerical values.

[0045] The second step is to query the design dimension group data of the aforementioned workpiece in the standard workpiece data information. This design dimension group data can be the standard design data corresponding to the production workpiece. In practice, first, the part number of the production workpiece can be determined. Then, the corresponding design dimension group data can be found in the standard workpiece data information based on the part number.

[0046] The third step is to determine the weight parameter information of the functional areas corresponding to the measured size group data, based on the preset functional area weight information. The preset functional area weight information can represent the importance of different feature dimensions on the workpiece. The weight parameter information can be a list of weight values ​​corresponding to the actual dimensions. In a workpiece production scenario, the weight parameter information could be "connecting hole diameter weight: 0.4, bearing diameter weight: 0.4, base thickness weight: 0.2". The workpiece can be a gearbox. The functional areas of the gearbox can include: bearing assembly area (bearing diameter), bolt connection area (connecting hole diameter), and base support area (base thickness).

[0047] The fourth step is to determine the relative deviation of each individual dimension between the measured dimension set and the designed dimension set. This relative deviation can be the difference between the measured value and the design value for each dimension. In a workpiece manufacturing scenario, first, the interpolation between the measured and design values ​​is determined. Then, the interpolation is normalized (by the ratio to half the tolerance) to obtain the relative deviation of each individual dimension.

[0048] Fifth, based on the aforementioned weighting parameters, the relative deviations of the individual dimensions are weighted by functional areas to obtain the dimensional deviation rate. This dimensional deviation rate can be a value obtained by fusing the relative deviations of individual dimensions according to the weights of each functional area. In the workpiece generation scenario, the workpiece can be a gear used in a gearbox. The weight of the bearing assembly area can be 0.5. For example, the actual measured value of the journal diameter can be 20.012 mm. The standard value of the journal diameter can be 20.00 mm. Then the dimensional deviation rate can be (20.012 mm - 20.00 mm) / 20.00 mm × 100% × 0.5 = 0.03%.

[0049] Step 6: Based on the workpiece inspection timestamps, extract the spindle load value sequence, feed rate value sequence, and vibration amplitude value sequence from the initial machine tool data associated with the workpiece production quality data. The spindle load value sequence can be a chronological sequence of the machine tool spindle motor output torque or current during the workpiece machining period. The feed rate value sequence can be a chronological sequence of the actual movement speeds of each axis of the machine tool during the workpiece machining period. The vibration amplitude value sequence can be a chronological sequence of the machine tool vibration intensity collected by vibration sensors during the workpiece machining period.

[0050] As an example, firstly, the processing time can be calculated backward from the workpiece inspection timestamp to determine the time window. Secondly, the corresponding data can be extracted from the initial machine tool data corresponding to the workpiece production quality data.

[0051] Step 7: Determine the load volatility corresponding to the aforementioned spindle load value sequence. This load volatility can be an indicator used to quantify the stability of the spindle load. In practice, the load volatility can be the ratio of the standard deviation to the mean of the spindle load value sequence.

[0052] Step 8: Determine the speed following deviation ratio corresponding to the above feed rate value sequence. The speed following deviation ratio can be an indicator used to quantify the response speed control command of the CNC machine tool. In practice, firstly, the deviation sequence (standard command speed - feed rate) corresponding to the feed rate value sequence can be determined based on the standard command speed. Then, the speed following deviation ratio is obtained by using the ratio of the deviation sequence to the standard command speed.

[0053] Step 9: Determine the vibration exceeding-limit data corresponding to the above vibration amplitude value sequence. The above vibration exceeding-limit data can be any data in the vibration amplitude value sequence that exceeds a preset safety threshold.

[0054] Step 10: Normalize the load volatility, speed following deviation ratio, and vibration exceeding limits data to obtain a cutting stability sequence. The cutting stability sequence can be a set of data obtained by normalizing the load volatility, speed following deviation ratio, and vibration exceeding limits data (e.g., maximum-minimum normalization).

[0055] Step 11: Based on the aforementioned preset functional area weight information, the cutting stability sequence is weighted and fused to obtain the cutting stability index. As an example, firstly, corresponding weights can be assigned to the three indicators in the cutting stability sequence according to the preset functional area weight information. Then, the weighted cutting stability sequences are weighted and summed to obtain the cutting stability index.

[0056] Step 105: In response to the dimensional deviation rate being greater than the first preset standard value and / or the cutting stability index being less than the second preset standard value, the tool parameter data corresponding to the CNC machine tool is searched in the preset process knowledge base.

[0057] In some embodiments, the execution entity may, in response to the dimensional deviation rate being greater than a first preset standard value and / or the cutting stability index being less than a second preset standard value, search for the tooling parameter data corresponding to the machining of the CNC machine tool in a preset process knowledge base. The first preset standard value may be a pre-set upper limit value for acceptable dimensional accuracy. The second preset standard value may be a pre-set lower limit value for acceptable stability of the CNC machine tool's production process. The tooling parameter data may be the process parameters for CNC machine tool machining. The preset process knowledge base may be a database storing expert experience and historical optimization schemes. In a workpiece production scenario, the first preset standard value may be "5%". When the deviation rate exceeds this threshold, the dimensional problem is serious, and the machine tool needs adjustment. The second preset standard value may be "0.65". When the cutting stability index is less than this threshold, the machining condition of the CNC machine tool is poor, and the machine tool needs adjustment. The tooling parameter data may include: cutting parameters (e.g., spindle speed, feed rate, and depth of cut), tool parameters (e.g., tool radius compensation, tool length compensation, and tool type), and other parameters (e.g., coolant switch).

[0058] As an example, firstly, the dimensional deviation rate and cutting stability index can be compared to obtain the comparison result (triggering subsequent steps). Secondly, based on the comparison result (dimensional deviation), the current CNC machine tool machining parameters, workpiece material, and tool type are determined, and a query statement is constructed. Then, the query statement is used to retrieve the corresponding tool parameter data from a preset process knowledge base.

[0059] In the process of adopting technical solutions to address the aforementioned technical problems, the following issues often arise: parameter solutions directly extracted from the knowledge base may not match the actual performance state of the machine tool (e.g., spindle wear, leadscrew backlash), posing an execution risk. The conventional solution is to establish a dedicated team of process engineers to manually analyze newly emerging problems and manually input verified and effective solutions into the knowledge base. However, considering the low efficiency of manual intervention and the inability to consistently and reliably reuse human experience, the inventors decided to adopt the following solution: In some optional implementations of certain embodiments, the execution entity may, in response to the dimensional deviation rate being greater than a first preset standard value and / or the cutting stability index being less than a second preset standard value, search for the tool parameter data corresponding to the machining of the CNC machine tool in a preset process knowledge base, which may include the following steps: The first step is to determine the business processing requirements corresponding to the aforementioned CNC machine tool, thereby obtaining the basic tooling parameter characteristics. These basic tooling parameter characteristics can be the process parameters set by the current CNC machine tool according to the type of processing business. In a workpiece production scenario, the aforementioned business processing requirements can refer to the specific requirements of the current production task. These business processing requirements can specify the parts to be processed (e.g., part number), the materials used (e.g., material grade), the processing quality (e.g., accuracy grade), and the planned output, providing the CNC machine tool with the task basis for workpiece processing. The aforementioned process parameters can include: cutting parameters (e.g., spindle speed, feed rate, and depth of cut), tool parameters (e.g., tool radius compensation, tool length compensation, and tool type), and other parameters (e.g., coolant switch).

[0060] The second step is to generate a unique operating condition fingerprint corresponding to the aforementioned basic equipment parameter features. This unique operating condition fingerprint can be a unique and fixed string identifier generated from the basic equipment parameter features using a hash algorithm. For example, the basic equipment parameter features can be a JSON string. A hash algorithm can be used to process the JSON string to obtain the unique operating condition fingerprint.

[0061] The third step involves querying the tool parameter optimization data corresponding to the unique working condition fingerprint in the aforementioned preset process knowledge base. This tool parameter optimization data can be parameter data that optimizes the basic parameter characteristics of the tool. In a workpiece production scenario, this tool parameter optimization data can include: tool compensation, spindle speed fine-tuning, and feed rate.

[0062] As an example, firstly, a query can be constructed using the unique operating condition fingerprint as the key field. Then, the corresponding equipment parameter optimization data can be queried from the preset process knowledge base.

[0063] Fourth step: In response to the fact that the above-mentioned appliance parameter optimization data is not empty, determine that the above-mentioned appliance parameter optimization data is appliance parameter data.

[0064] Fifth, in response to the above appliance parameter optimization data being empty, the following appliance parameter data determination steps are performed: The first sub-step involves acquiring the machining tool parameter data of the aforementioned CNC machine tool. This machining tool parameter data can be the original process parameters currently being processed by the CNC machine tool. In practice, the current parameters can be read from the corresponding variables of the CNC system via an edge gateway. In a workpiece production scenario, the aforementioned original process parameters can be the real-time process parameters currently driving the CNC machine tool to perform workpiece machining (e.g., cutting, feed, and tool change).

[0065] The second sub-step involves analyzing the aforementioned machining tool parameter data to obtain a dimensional position distribution matrix, a stability index decay curve, and tool wear thermo-coupling values. The dimensional position distribution matrix can be a binary array (e.g., describing the distribution of machining errors at different spatial locations on the workpiece). The stability index decay curve can be a data sequence describing the trend of the cutting stability index as tool usage time (or machining quantity) increases. The tool wear thermo-coupling values ​​can be indicators reflecting the tool wear state. In a workpiece production scenario, the rows and columns of the dimensional position distribution matrix can be two-dimensional coordinates of the workpiece's spatial location. The elements of the dimensional position distribution matrix can be errors at corresponding row and column positions. For example, the workpiece can be a gear. The rows of the gear workpiece's dimensional position distribution matrix can be the distance from the center to the edge. For example, row 1: radial position R = 10mm (near the center); row 2: radial position R = 30mm (middle area); row 3: radial position R = 50mm (middle area). The columns of the gear workpiece's dimensional position distribution matrix can be circumferential angles around the center. For example, column 1: circumferential angle θ = 0° (first tooth groove position), column 2: circumferential angle θ = 30° (second tooth groove position). The elements of the gear workpiece's dimensional position distribution matrix can be the deviation between the actual machined dimensions and the design dimensions. For example, the element in the 3rd row and 2nd column of the matrix element could be +0.015mm. This could represent a radial distance R = 50mm (tooth root circle), and the position of circumferential angle θ = 30° (second tooth groove), where the actual machined dimension is 0.015mm larger than the design dimension.

[0066] As an example, the aforementioned size and position distribution matrix can be generated by analyzing the tooling parameter data of a batch of workpieces, statistically analyzing the size deviations of different workpiece feature positions, and then combining them into a matrix representation. The aforementioned stability index decay curve can be obtained by querying a historical database, extracting the cutting stability index obtained after the tool is mounted on the machine from the machining tooling parameter data, and plotting it in chronological order to obtain the stability index decay curve. The aforementioned tool wear thermo-coupling value can be obtained through the following steps: First, determine the difference between the current spindle load and the initial spindle load in the machining tooling parameter data. Then, divide the difference by the initial spindle load to obtain a first ratio. Next, multiply the first interpolation by a first weight (e.g., 0.4) according to a preset weight allocation to obtain a first product. Then, multiply the spindle bearing temperature by a second weight (e.g., 0.6) to obtain a second product. Finally, add the first product and the second product to obtain the tool wear thermo-coupling value.

[0067] The third sub-step involves constructing a dynamic operating condition code using the aforementioned size and position distribution matrix, the aforementioned stability index decay curve, and the aforementioned tool wear thermo-coupling value. This dynamic operating condition code can be a feature code for fuzzy querying, constructed based on the machine tool's real-time status and performance degradation.

[0068] The fourth sub-step involves using the aforementioned dynamic operating condition coding to query the corresponding initial tooling parameter data in the aforementioned preset process knowledge base. The aforementioned initial tooling parameter data can be process parameters that are similar to the current operating condition.

[0069] The fifth sub-step involves correcting the initial tooling parameter data using the aforementioned dimensional deviation rate and cutting stability index to obtain the tooling parameter data. This correction can be based on process knowledge of the workpiece machining to optimize the tooling parameters. For example, in a workpiece production scenario, when the dimensional deviation rate exceeds a preset threshold, the tool radius compensation in the initial tooling parameter data can be reduced proportionally to the ratio of the dimensional deviation rate to the preset threshold. Similarly, when the cutting stability index is less than a preset threshold, the rotational speed or feed rate in the initial tooling parameter data can be reduced proportionally to the ratio of the cutting stability index to the preset threshold.

[0070] The above-described steps, as an inventive point of this disclosure, solve the technical problem mentioned in the background art: "Under new working conditions (e.g., new materials, new tool combinations), the process knowledge base cannot provide effective optimization parameters due to a lack of historical data." In practice, when the system faces a completely new machining task with no record in the knowledge base, it cannot provide tooling optimization parameters for the current CNC machine tool or can provide potentially unsafe default parameters. This can lead to production interruptions or batch scrap, resulting in waste of materials and time. This disclosure designs a scheme that integrates precise matching of working condition fingerprints and dynamic working condition coding fuzzy reasoning. When precise tooling optimization parameters are unavailable, it can autonomously generate tooling optimization parameters by searching for CNC machine tool optimization parameters for similar workpiece machining and combining them with the actual state of the current CNC machine tool (e.g., tool wear, machine tool stability). Therefore, it avoids the risks of production interruptions due to lack of data and the blind use of unsafe parameters, enabling the generation of tooling optimization parameters based on the actual state of the machine tool, reducing trial-and-error costs and material waste, and ensuring the continuity of workpiece production.

[0071] In addressing the aforementioned technical problems using technical solutions, the following issues often arise: current process knowledge bases have significant limitations: insufficient matching accuracy, making it difficult to accurately distinguish fundamental differences under similar anomalies. Furthermore, recommended historical optimization schemes do not align with the current state of the machine tools and cutting tools, resulting in low parameter applicability. Directly applying these recommended parameters may exceed the current performance limits of the machine tool, thereby posing equipment safety risks. Conventional solutions typically involve expanding the sample size of the knowledge base to cover more operating conditions. However, considering that static matching relying on historical data cannot adapt to the complex, dynamically changing environment of the production site, and would also increase maintenance burden and reduce query efficiency, the inventors decided to adopt the following solution: In some optional implementations of certain embodiments, the execution entity may, in response to the dimensional deviation rate being greater than a first preset standard value and / or the cutting stability index being less than a second preset standard value, search for the tool parameter data corresponding to the machining of the CNC machine tool in a preset process knowledge base, which may include the following steps: The first step is to determine the type of quality anomaly generated based on the aforementioned dimensional deviation rate and / or cutting stability index. The aforementioned type of quality anomaly generated can be the type of cause for the abnormality in the dimensional deviation rate and / or cutting stability index.

[0072] As an example, the anomaly type could be determined based on pre-defined process knowledge. For instance, if the dimensional deviation rate is greater than 5% and the cutting stability index is less than 0.7, then the anomaly type could be tool wear.

[0073] The second step involves matching the target optimization parameter set with the generated quality anomaly type and the workpiece's material properties from the historical process knowledge base. This historical process knowledge base can be a database storing a large number of historical machining cases. The target optimization parameter set can be a collection of one or more historical optimization solutions from the historical process knowledge base that match the current anomaly type and material properties. In the workpiece production scenario, the historical machining cases can include the problem at that time (anomaly type), the working conditions (material, tooling), and the final solution (optimization parameters).

[0074] The third step is to determine the tool wear level based on the tool wear amount of the CNC machine tool. The tool wear amount can be a quantified value of the current degree of tool wear. The tool wear level can be a preset, discretized version of the continuous wear amount, divided into several levels. For example, the levels could be "0-0.1mm, new tool", "0.1-0.3mm, slight wear", and "above 0.3mm, severe wear". In a workpiece production scenario, the tool wear amount could be 0.38mm. Therefore, the corresponding tool wear level would be severe wear.

[0075] The fourth step is to extract the initial tooling parameter data corresponding to the tool wear level from the aforementioned target optimization parameter set. The initial tooling parameter data can be parameters selected from the target optimization parameter set that match the current tool wear level.

[0076] The fifth step is to perform conflict detection on the initial machine tool data and the initial fixture parameter data. This conflict detection determines whether there are any contradictions between the initial fixture parameter data and the current actual state of the machine tool (initial machine tool data). In practice, this conflict detection may verify whether each fixture parameter in the initial fixture parameter data is within the maximum limits of the CNC machine tool data.

[0077] Step 6: In response to the failure of the above conflict detection, the above initial instrument parameter data is determined to be instrument parameter data.

[0078] Step 7: In response to the successful conflict detection, parameter constraint processing is performed based on the maximum load threshold of the CNC machine tool and the surface roughness in the workpiece production quality data to generate optimized parameters. This parameter constraint processing can be an optimization process. In the workpiece production scenario, this optimization process can use initial tool parameters as the optimization target, constrained by the maximum load threshold of the CNC machine tool and the workpiece surface roughness requirements. The optimized parameters can be new parameters that ensure machining quality within the safe operating range of the CNC machine tool.

[0079] As an example, first, the optimization objective can be determined (e.g., the difference between the optimized parameters and the initial tooling parameter data). Second, the constraints could be that the load parameter in the optimized parameters is less than the maximum load threshold of the CNC machine tool, or that the workpiece surface roughness in the optimized parameters is less than the roughness required by the workpiece quality standards. Finally, the gradient descent algorithm is used for optimization to obtain the specific parameter values ​​in the optimized parameters.

[0080] Step 8: Using the aforementioned optimization parameters, optimize the initial instrument parameter data to obtain the instrument parameter data. As an example, first, determine the parameter fields to be optimized in the optimization parameters. Then, query the parameter fields in the initial instrument parameter data and replace the corresponding parameters with the values ​​from the optimization parameters to obtain the instrument parameter data.

[0081] Optionally, the aforementioned historical technology knowledge base can be created through the following steps: The first step is to acquire the tooling parameters, process quality data, and CNC machine tool operating status data for historical machining tasks. These historical machining tasks can be completed work orders with a clear result (success or failure). The process quality data can be the quality inspection results of the workpieces produced by the task. The CNC machine tool operating status data can be the real-time status data of the CNC machine tool during the machining process.

[0082] The second step is to label the anomaly types based on the aforementioned process quality data. These anomaly type labels can be classification tags assigned to each historical processing task based on the quality data, used to identify quality problems present in that task. In practice, firstly, engineers perform quality inspections on the workpieces. Then, based on the inspection results, they label the processing tasks with the corresponding anomaly type tags.

[0083] The third step involves using a clustering algorithm to cluster the aforementioned tool parameters, process quality data, and CNC machine tool operating status data based on the aforementioned anomaly type labels, resulting in a parameter optimization set. This set can be a collection of multiple clusters formed after clustering. In a workpiece production scenario, the parameter optimization set can include workpiece quality data, CNC machine tool operating data, and tool parameter data under the same anomaly type.

[0084] The fourth step involves adding applicable material information to each parameter optimization group in the aforementioned parameter optimization set to obtain a process parameter set, which serves as a preset process knowledge base. The applicable material information includes: the applicable material range and the applicable tool wear level. Specifically, the applicable material information can refer to the workpiece material type to which the parameter optimization group is applicable. In a workpiece production scenario, the applicable material range can be a refinement of the material information. The applicable material range can refer to the hardness range or a specific grade of the material. The applicable tool wear level can indicate which stage of tool wear the parameter optimization group is applicable to.

[0085] The above-described operation steps, as an inventive point of this disclosure, solve the technical problem mentioned in the background art: "When quality problems occur, adjusting machining parameters (e.g., spindle speed, feed rate, tool compensation) relies on experienced engineers to identify and correct the problem. Real-time, automatic adjustment of the CNC machine tool is impossible, resulting in slow response and wasted machining materials." In practice, simple case matching often ignores key status information such as tool wear and machine tool performance degradation, leading to recommended tool optimization parameters that exacerbate machining problems and even trigger CNC machine tool alarms. This disclosure designs a scheme based on root cause diagnosis, multi-dimensional status matching (e.g., workpiece anomaly type, workpiece material, and CNC machine tool tool wear), and tool parameter optimization. Based on the current production quality type of the workpiece, it finds the tool adjustment parameters under historical conditions and uses the real-time operating status of the tool and machine tool as the core decision-making basis. The tool adjustment parameters are constrained to ensure they fit the actual situation of the CNC machine tool. Therefore, it significantly improves the response speed and quality control level of CNC machining, reduces reliance on human experience, and effectively reduces workpiece material waste and equipment downtime.

[0086] Step 106: Convert the instrument parameter data into machine tool execution instructions.

[0087] In some embodiments, the aforementioned execution entity can convert the aforementioned instrument parameter data into machine tool execution instructions. These machine tool execution instructions can be codes (e.g., G-code) that the CNC machine tool control system can directly recognize and execute.

[0088] As an example, firstly, specific numerical values ​​can be extracted from the tool parameter data. Then, the extracted values ​​are mapped to the corresponding code instructions to obtain the machine tool execution instructions.

[0089] In the process of adopting technical solutions to address the aforementioned technical problems, the following issues often arise: the generated initial machine tool instructions conform to basic machining logic but do not consider machining dynamics, which may lead to cutting vibration, low efficiency, or even damage to CNC machine tool equipment (e.g., cutting tools). Simultaneously, the lack of a verification mechanism, with optimized instructions being directly issued and executed on related physical equipment (e.g., cutting tools), may pose risks of collision and damage. Conventional solutions typically rely on engineers to manually review and optimize the instruction code, followed by trial runs on a CNC machine tool. However, the inventors considered that relying on engineers for review would increase time and inefficiency. Over-reliance on personal experience makes large-scale application difficult. Verifying instructions on the machine tool would lead to material waste. Therefore, we decided to adopt the following solution: In some optional implementations of certain embodiments, the execution entity can convert the aforementioned instrument parameter data into machine tool execution instructions, which may include the following steps: The first step is to extract the process parameter values ​​from the aforementioned tool parameter data. These process parameter values ​​can be the parameters that drive the CNC machine tool to perform various processes within the tool parameter data. In a workpiece production scenario, these process parameter values ​​may include: spindle speed (1500 RPM) and feed rate (1000 mm / min). In practice, the corresponding process parameter values ​​can be extracted from the tool parameter data using a key-value query method.

[0090] The second step is to fill the aforementioned process parameter values ​​into the corresponding positions of the preset instruction template to obtain the initial machine tool instructions. The preset instruction template can be a program template containing placeholders and conforming to the target CNC machine tool controller syntax (e.g., G-code). In a workpiece production scenario, the preset instruction template can include workpiece machining steps and toolpaths (e.g., rapid traverse, cutting, and finally return).

[0091] The third step involves optimizing the toolpath of the initial machine tool instructions using a pre-trained instruction optimization model to obtain optimized machine tool instructions. The instruction optimization model can be a software model trained based on reinforcement learning. The input to the instruction optimization model can be code executable by the CNC machine tool (e.g., G-code). The toolpath optimization can be a process of adjusting and optimizing the tool movement trajectory described in the instruction code.

[0092] The fourth step involves sending the optimized machine tool instructions to the corresponding CNC machine tool digital twin model to obtain simulation results. This CNC machine tool digital twin model can be a virtual CNC machine tool simulation environment. It can be a digital model simulating the geometry (e.g., 3D model), kinematic logic, control system behavior, and physical characteristics (e.g., rigidity, speed) of a physical machine tool. The simulation results can be a report output by the digital twin after completing the virtual machining process.

[0093] As an example, firstly, machine tool commands can be sent to the digital twin platform via an API interface. Then, the digital twin platform can issue the commands to the corresponding CNC machine tool digital twin model and obtain the simulation results. Finally, the simulation results can be retrieved via the API interface.

[0094] Fifth, in response to the simulation results meeting the preset results, the optimized machine tool instructions are determined as machine tool execution instructions.

[0095] Step 6: In response to the simulation results not meeting the preset requirements, a failure message is sent to the human interaction port for manual code verification. The failure message can be data extracted from the simulation report describing the cause of the failure. The human interaction port can be an interface displaying the abnormal task requiring manual handling and its details (e.g., a front-end display page and message notifications). The manual code verification can be a process where professionals review the failure message, analyze the machine tool instructions (e.g., G-code), and make modifications and confirmations.

[0096] As an example, you could first construct a message containing all the necessary context (e.g., artifact ID, failure code, simulation report link). Then, you could send that message to a human interaction portal (e.g., a front-end display page, email, or a communication tool) via an API call.

[0097] Optionally, the training set of the above instruction optimization model may include: programs corresponding to historical machining tasks (e.g., NC programs); machine tool operation data recorded synchronously with each NC program (e.g., spindle load current sequence, vibration data of each axis); workpiece machining quality data; and expert optimization data (e.g., modifications to the original program and the results of the modifications). The basic model of the above instruction optimization model may be a Transformer network model. The above instruction optimization model may be obtained using a reinforcement learning algorithm (e.g., proximal policy optimization). The above reinforcement learning algorithm may include: agent, environment, action, state, and reward. In the workpiece production scenario, the above agent may be an instruction optimization model. The above environment may be a simulated CNC machine tool machining environment (digital twin model). The above action may be an operation on the instruction code (e.g., adding a deceleration command to line 4 of the code). The above state may be the current instruction code segment and the instruction code context. The above reward may include: if the estimated machining time is shortened after modifying the instruction code, a reward is given. If modifying the instruction code results in a more stable estimated cutting force (reduced load fluctuation) or an improved estimated surface roughness, a reward is given. If modifying the instruction code leads to an estimated collision or exceeds the machine tool's performance limits, a penalty is imposed.

[0098] The above-described operation steps, as an inventive point of this disclosure, solve the technical problem mentioned in the background art: "When quality problems occur, adjusting machining parameters (e.g., spindle speed, feed rate, tool compensation) relies on experienced engineers to identify and correct the problem. Real-time, automatic adjustment of the CNC machine tool is impossible, resulting in slow response and waste of machining materials." In practice, the lack of optimized and verified instruction codes easily leads to equipment collision risks on CNC machine tools, resulting in decreased workpiece machining quality or damage to the CNC machine tool's equipment (tools). This disclosure designs an instruction production scheme based on digital twin simulation verification. During the code generation stage, expert experience is incorporated into a reinforcement learning model to improve instruction quality. Before issuance, simulation experiments are conducted using a digital twin model for zero-cost safety and performance verification, ensuring the reliability and safety of the output instructions. Therefore, correct and simulation-verified instruction codes can reduce equipment damage to CNC machine tools caused by instruction errors, thereby reducing workpiece material waste. Requiring manual correction of erroneous simulation results and instruction codes reduces reliance on human intervention.

[0099] Step 107: Write the machine tool execution instructions into the control system of the CNC machine tool to perform workpiece processing.

[0100] In some embodiments, the aforementioned executing entity can write the machine tool execution instructions into the control system of the CNC machine tool for workpiece machining. The control system is responsible for parsing the received machine tool execution instructions, converting them into electrical signals, and then driving the execution components (e.g., motors, spindle motors) to coordinate the movement of the machine tool. The workpiece machining process can be a process in which the control system begins to execute instructions one by one, controlling the machine tool to complete the cutting of the blank, and ultimately producing a workpiece that meets the requirements.

[0101] The various embodiments of this disclosure have the following beneficial effects: Through the CNC machine tool adjustment methods of some embodiments of this disclosure, the CNC machine tool can adjust parameters in real time according to the quality of the workpiece, improving the machining quality and yield of the workpiece. Specifically, the reason for the low workpiece yield is that, due to post-production sampling inspection, when workpiece quality defects are discovered, the CNC machine tool has already produced unqualified workpieces, leading to serious material waste. Based on this, the CNC machine tool adjustment methods of some embodiments of this disclosure first collect real-time data of the CNC machine tool through an edge gateway to obtain initial machine tool data. This allows for real-time acquisition of data during the machining process, providing a data foundation for subsequent analysis. Second, the workpieces produced by the CNC machine tool are inspected in real time to obtain workpiece inspection data. This transforms quality control from offline sampling inspection to online inspection, achieving real-time quality supervision. Then, the initial machine tool data and the workpiece inspection data are bound together to obtain workpiece production quality data. This establishes a mapping relationship between the machining parameters of the CNC machine tool and the workpiece quality results, realizing full-process quality traceability. Next, based on standard workpiece data, the production quality data of the aforementioned workpiece is evaluated to obtain the dimensional deviation rate and cutting stability index. This achieves quantitative evaluation and real-time monitoring of the machining status, providing a decision-making basis for accurately adjusting the CNC machine tool. Subsequently, in response to the dimensional deviation rate exceeding a first preset standard value and / or the cutting stability index falling below a second preset standard value, the corresponding tool parameter data for machining on the CNC machine tool is retrieved from the preset process knowledge base. Thus, the optimization scheme is matched using the expert knowledge base, replacing the CNC machine tool adjustment mode that relies on manual experience. Then, the tool parameter data is converted into machine tool execution instructions. This achieves automatic conversion from optimization strategy to executable code. Finally, the machine tool execution instructions are written into the control system of the CNC machine tool for workpiece machining. This completes the closed-loop and automated control of the CNC machine tool from machining parameters to adjustment instructions, ensuring that the optimization strategy can be applied to the workpiece production process in real time. In summary, by adjusting and controlling CNC machine tools through real-time data acquisition, online quality inspection, data fusion analysis, intelligent decision-making, and automatic execution, the automatic adjustment of the CNC machine tool processing process and the stable improvement of workpiece quality are realized. Machine tool parameters can be controlled in real time according to the processing quality status, thereby improving workpiece processing quality, reducing the defect rate, and increasing production efficiency.

[0102] Further reference Figure 2 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of a CNC machine tool adjustment device, which are similar to... Figure 1 Corresponding to the method embodiments shown, this CNC machine tool adjustment device can be specifically applied to various electronic devices.

[0103] like Figure 2As shown, a CNC machine tool adjustment device 200 includes: a data acquisition unit 201, a workpiece detection unit 202, a data binding unit 203, a quality assessment unit 204, a parameter lookup unit 205, an instruction generation unit 206, and a machine tool control unit 207. The data acquisition unit 201 is configured to: acquire real-time data of the CNC machine tool through an edge gateway to obtain initial machine tool data. The workpiece detection unit 202 is configured to: perform real-time detection on the workpieces produced by the CNC machine tool to obtain workpiece detection data. The data binding unit 203 is configured to: bind the initial machine tool data and the workpiece detection data to obtain workpiece production quality data. The quality assessment unit 204 is configured to: perform production quality assessment on the workpiece production quality data based on standard workpiece data information to obtain dimensional deviation rate and cutting stability index. The parameter lookup unit 205 is configured to: in response to the dimensional deviation rate being greater than a first preset standard value and / or the cutting stability index being less than a second preset standard value, search for the tool parameter data corresponding to the machining of the CNC machine tool in a preset process knowledge base. The instruction generation unit 206 is configured to: convert the tool parameter data into machine tool execution instructions. The machine tool control unit 207 is configured to: write the machine tool execution instructions into the control system of the CNC machine tool for workpiece machining.

[0104] It is understandable that the units described in the CNC machine tool adjustment device 200 are related to the reference. Figure 1 The steps described in the method correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method also apply to the CNC machine tool adjustment device 200 and the units contained therein, and will not be repeated here.

[0105] The following is for reference. Figure 3 It shows a schematic diagram of the structure of an electronic device (e.g., an electronic device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0106] like Figure 3 As shown, the electronic device 300 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0107] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0108] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 309, or installed from storage device 308, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of some embodiments of this disclosure.

[0109] It should be noted that, in some embodiments of this disclosure, the computer-readable medium described above may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0110] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0111] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: acquire real-time data of the CNC machine tool through an edge gateway to obtain initial machine tool data; perform real-time detection on the workpiece produced by the CNC machine tool to obtain workpiece detection data; bind the initial machine tool data and the workpiece detection data to obtain workpiece production quality data; perform production quality evaluation on the workpiece production quality data based on standard workpiece data information to obtain dimensional deviation rate and cutting stability index; respond to the dimensional deviation rate being greater than a first preset standard value and / or the cutting stability index being less than a second preset standard value, search for the tool parameter data corresponding to the CNC machine tool in a preset process knowledge base; convert the tool parameter data into machine tool execution instructions; and write the machine tool execution instructions into the control system of the CNC machine tool to perform workpiece machining.

[0112] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0113] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0114] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including a data acquisition unit, a workpiece inspection unit, a data binding unit, a quality assessment unit, a parameter lookup unit, an instruction generation unit, and a machine tool control unit. The names of these units do not necessarily limit the specific unit; for example, a data acquisition unit may also be described as "a unit that collects real-time data from a CNC machine tool through an edge gateway to obtain initial machine tool data."

[0115] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0116] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A numerical control machine tool adjustment method, comprising: collecting real-time data of a numerical control machine tool through an edge gateway to obtain initial machine tool data; real-time detecting workpieces produced by the numerical control machine tool to obtain workpiece detection data; binding the initial machine tool data and the workpiece detection data to obtain workpiece production quality data; based on standard workpiece data information, performing production quality evaluation on the workpiece production quality data to obtain a size deviation rate and a cutting stability index; in response to the size deviation rate being greater than a first preset standard value and / or the cutting stability index being less than a second preset standard value, searching for tool parameter data corresponding to machining of the numerical control machine tool in a preset process knowledge base; converting the tool parameter data into machine tool execution instructions; writing the machine tool execution instructions into a control system of the numerical control machine tool to perform workpiece machining.

2. The method of claim 1, wherein, The collecting real-time data of a numerical control machine tool through an edge gateway to obtain initial machine tool data comprises: physically connecting the edge gateway to a control system of the numerical control machine tool; configuring a communication protocol driver compatible with the control system in the edge gateway to perform communication connection to obtain a communication connection channel; defining data collection tags in the edge gateway based on a data source address corresponding to the communication connection channel to obtain a set of data collection tags; based on the data source address, collecting data of each data collection tag in the set of data collection tags to obtain a set of real-time data; integrating each real-time data in the set of real-time data to obtain initial machine tool data.

3. The method of claim 1, wherein, The real-time detecting workpieces produced by the numerical control machine tool to obtain workpiece detection data comprises: deploying an online detection device in a machining area of the numerical control machine tool; in response to completion of machining of the workpiece, collecting quality characteristic data of the workpiece in real time through the online detection device; associating the quality characteristic data with unique identification information of the workpiece to obtain workpiece detection data.

4. The method of claim 1, wherein, The binding the initial machine tool data and the workpiece detection data to obtain workpiece production quality data comprises: extracting workpiece unique identification information and detection time stamps in the workpiece detection data; based on the detection time stamps, matching numerical control machine tool operation parameter data of a corresponding time window from the initial machine tool data; establishing a data mapping relationship among the workpiece unique identification information, the numerical control machine tool operation parameter data, and the workpiece detection data; structurally packaging the data mapping relationship to obtain workpiece production quality data.

5. The method of claim 1, wherein, The based on standard workpiece data information, performing production quality evaluation on the workpiece production quality data to obtain a size deviation rate and a cutting stability index comprises: extracting measured size group data and workpiece detection time stamps from the workpiece production quality data; querying design size group data of the workpiece in the standard workpiece data information; based on preset functional area weight information, determining weight parameter information of a functional area corresponding to the measured size group data; determining a single-size relative deviation of the measured size group data and the design size group data; According to the weight parameter information, the single size relative deviation is functionally weighted to obtain a size deviation rate; According to the workpiece detection timestamp, a spindle load value sequence, a feed speed value sequence and a vibration amplitude value sequence are extracted from initial machine tool data associated with the workpiece production quality data; A load fluctuation rate corresponding to the spindle load value sequence is determined; A speed following deviation ratio corresponding to the feed speed value sequence is determined; Vibration overrun data corresponding to the vibration amplitude value sequence is determined; The load fluctuation rate, the speed following deviation ratio and the vibration overrun data are normalized to obtain a cutting stability sequence; According to the preset function area weight information, the cutting stability sequence is weighted and fused to obtain a cutting stability index.

6. A numerical control machine tool adjusting device, comprising: a data acquisition unit configured to collect real-time data of a numerical control machine tool through an edge gateway to obtain initial machine tool data; a workpiece detection unit configured to detect workpieces produced by the numerical control machine tool in real time to obtain workpiece detection data; a data binding unit configured to bind the initial machine tool data and the workpiece detection data to obtain workpiece production quality data; a quality evaluation unit configured to evaluate the production quality of the workpiece production quality data based on standard workpiece data information to obtain a size deviation rate and a cutting stability index; a parameter searching unit configured to, in response to the size deviation rate being greater than a first preset standard value and / or the cutting stability index being less than a second preset standard value, search for tool parameter data corresponding to machining of the numerical control machine tool in a preset process knowledge base; an instruction generation unit configured to convert the tool parameter data into machine tool execution instructions; a machine tool control unit configured to write the machine tool execution instructions into a control system of the numerical control machine tool for workpiece machining.

7. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, when the one or more programs are executed by the one or more processors, the one or more processors implement the method of any one of claims 1-5.

8. A computer readable medium having stored thereon a computer program, wherein, The program is executed by the processor to implement the method of any one of claims 1-5. The program is executed by the processor to implement the method of any one of claims 1-5.

Images