Mold processing precision control method, device, equipment and storage medium

Abstract

The present invention discloses a mold processing precision control method, device, equipment and storage medium, including: obtaining tolerances and initial programming allowances for multiple preset feature surfaces to be processed by a part to be processed, wherein the tolerances and / or initial programming allowances of each feature surface are not exactly the same; in the process of processing any feature surface, periodically detecting the state deviation of the feature surface, and when it is detected that the state deviation is greater than the deviation threshold, calling the PID algorithm to compensate and update the current programming allowance, wherein the larger the value of the state deviation, the greater the compensation for the current programming allowance; adjusting the processing parameters currently used to process the feature surface, and combining the compensated current programming allowance with the adjusted processing parameters to continue processing the feature surface. The mold processing precision control method, device, equipment and storage medium disclosed in the present application solve the problem that the processing precision of the existing processing method cannot be guaranteed, thereby effectively improving the technical effect of the processing precision of the feature surface.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of mold processing, and in particular to a mold processing precision control method, device, equipment and storage medium. Background Art

[0002] Mold processing refers to the process of manufacturing forming tools (such as stamping molds, injection molds, etc.) and blanking tools. It is usually composed of an upper mold and a lower mold. The material is formed by a press and is widely used in electronic connectors, automotive parts and other fields.

[0003] Some mold manufacturing techniques rely on manual experience and apply a uniform machining standard to all surface features of the component being machined. However, these machining methods cannot accommodate the varying precision requirements of the component's surface features, resulting in wasted resources in high-precision areas and a lack of guaranteed machining accuracy. Summary of the Invention

[0004] The purpose of the present invention is to at least provide a mold processing accuracy control method, device, equipment and storage medium, which can at least solve the technical problem that the above-mentioned processing method cannot process the feature surfaces according to the different precision requirements of the parts to be processed, which easily leads to waste of resources in high-precision areas and the processing accuracy cannot be guaranteed. At least it can achieve this by processing different feature surfaces with different precisions to realize precision graded control, and compensate and update the current programming allowance through the PID algorithm to perform dynamic compensation, and then continue to process the feature surface in combination with the adjusted processing parameters, thereby effectively improving the technical effect of the processing accuracy of the feature surface.

[0005] To solve the above technical problems, at least one embodiment of the present application provides a mold processing precision control method, comprising:

[0006] For a plurality of preset feature surfaces to be machined of a component to be machined, obtaining a tolerance and an initial programming allowance corresponding to each of the feature surfaces, wherein the tolerances and / or initial programming allowances of the feature surfaces are not completely the same;

[0007] During the processing of any of the feature surfaces, the state deviation of the feature surface is periodically detected. When it is detected that the state deviation is greater than a deviation threshold, a PID algorithm is called to compensate and update the current programming margin. The larger the value of the state deviation is, the greater the compensation amount for the current programming margin is.

[0008] Adjusting the machining parameters currently used for machining the characteristic surface, and continuing to machine the characteristic surface in combination with the compensated current programming allowance and the adjusted machining parameters;

[0009] When it is detected that the state deviation is greater than the deviation threshold, calling the PID algorithm to compensate and update the current programming margin includes:

[0010] When it is detected that the state deviation is greater than the deviation threshold, calculating the compensation amount for the current programming margin based on the state deviation by using the PID algorithm;

[0011] The compensation amount is added to the current programming margin to obtain the compensated current programming margin.

[0012] At least one embodiment of the present application further provides a mold processing precision control device, comprising:

[0013] An acquisition module is used to acquire, for a plurality of preset characteristic surfaces to be machined of a component to be machined, a tolerance and an initial programming allowance corresponding to each of the characteristic surfaces, wherein the tolerances and / or initial programming allowances of the characteristic surfaces are not completely the same;

[0014] a compensation module, configured to periodically detect a state deviation of any of the feature surfaces during machining, and when it is detected that the state deviation is greater than a deviation threshold, invoke a PID algorithm to compensate and update the current programming margin, wherein a greater value of the state deviation indicates a greater compensation amount for the current programming margin;

[0015] The first adjustment module is used to adjust the processing parameters currently used to process the characteristic surface, and continue to process the characteristic surface in combination with the compensated current programming allowance and the adjusted processing parameters.

[0016] At least one embodiment of the present application also provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the above-mentioned mold processing accuracy control method.

[0017] At least one embodiment of the present application further provides a computer-readable storage medium storing a computer program, which implements the above-mentioned mold processing accuracy control method when executed by a processor.

[0018] The mold processing precision control method, device, equipment and storage medium provided by the embodiments of the present application obtain the tolerance and initial programming allowance corresponding to each feature surface for multiple preset feature surfaces to be processed by the part to be processed. During the process of processing any feature surface, the state deviation of the feature surface is periodically detected. When the state deviation is detected to be greater than the deviation threshold, the PID algorithm is called to compensate and update the current programming allowance. Specifically, when the state deviation is detected to be greater than the deviation threshold, the compensation amount for the current programming allowance is calculated based on the state deviation by the PID algorithm; the compensation amount is superimposed on the current programming allowance to obtain the compensated current programming allowance. Then, the processing parameters currently used to process the feature surface are adjusted, and the feature surface is continued to be processed by combining the compensated current programming allowance with the adjusted processing parameters. In this way, by processing different feature surfaces with different precisions, precision graded control is achieved, and the current programming allowance is compensated and updated by the PID algorithm to perform dynamic compensation, and the feature surface is continued to be processed by combining the adjusted processing parameters, effectively improving the processing precision of the feature surface.

[0019] In some optional embodiments, the method further includes:

[0020] Constructing a mapping table containing different feature faces, and the feature identifiers and tolerances corresponding to each feature face;

[0021] Setting an initial programming margin corresponding to each of the characteristic surfaces, and constructing a mapping table including different characteristic surfaces and the initial programming margin corresponding to each characteristic surface;

[0022] The obtaining of the tolerance and initial programming margin corresponding to each of the feature surfaces includes:

[0023] Based on the feature identifiers of the feature surfaces pre-defined in the software model library, the tolerance and initial programming margin corresponding to each feature surface are matched from the mapping table.

[0024] In this way, the tolerance and initial programming allowance corresponding to the feature surface can be quickly obtained, which can effectively reduce the reliance on manual experience.

[0025] In some optional embodiments, the state deviation of the characteristic surface is calculated by the following steps:

[0026] In the process of machining the characteristic surface, periodically obtaining the size deviation, temperature deviation and stress deviation of the characteristic surface;

[0027] The size deviation, the temperature deviation, and the stress deviation obtained in the same cycle are fused and calculated to obtain the state deviation.

[0028] In this way, by fusing the data transmitted by sensors at different locations, multi-sensor data fusion is achieved, making the obtained state deviation more accurate.

[0029] In some optional embodiments, adjusting the processing parameters currently used to process the feature surface includes:

[0030] The characteristic parameters of the currently processed component and the mold used to process the component are input into a pre-built processing prediction model for prediction, and predicted processing parameters that match the characteristic parameters of the currently processed component and the mold used to process the component are obtained, and the predicted processing parameters are used as the adjusted processing parameters.

[0031] In this way, by dynamically adjusting the processing parameters of different feature surfaces, the adjusted processing parameters are more suitable for the feature surfaces in the current processing process, and the feature surfaces are continued to be processed based on the adjusted processing parameters, which can effectively improve the processing accuracy of the feature surfaces.

[0032] In some optional embodiments, the characteristic parameters of the currently processed component include the material hardness of the component, the characteristic parameters of the mold used to process the component include the wear and vibration frequency of the tool on the mold, and the processing parameters include the spindle speed and feed speed of the processing machine tool used to control the tool;

[0033] The processing prediction model is obtained by the following steps:

[0034] Build the original model;

[0035] The characteristic parameter samples of the component in the historical processing state for multiple time periods, the characteristic parameter samples of the mold used to process the component, and the corresponding processing parameter samples are obtained. The qualified rate of the processed products corresponding to the samples in each time period is constrained, and the reinforcement learning algorithm is used to train the original model to obtain the processing prediction model.

[0036] In this way, by training the original model with sample data constrained by the pass rate, the prediction accuracy of the obtained processing prediction model is improved.

[0037] In some optional embodiments, the method further includes:

[0038] When it is detected that the state deviation is less than or equal to the deviation threshold, the processing parameters currently used for processing the feature surface are directly adjusted, and the feature surface is continued to be processed based on the adjusted processing parameters.

[0039] In this way, the characteristic surface is continuously processed according to the adjusted processing parameters, which can effectively improve the processing accuracy of the characteristic surface. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] One or more embodiments are exemplarily described by the figures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments.

[0041] Figure 1 This is a flow chart of a mold processing precision control method provided by an embodiment of the present application;

[0042] Figure 2 This is a flow chart of a mold processing precision control device provided by an embodiment of the present application;

[0043] Figure 3 is a structural diagram of an electronic device provided by another embodiment of the present application;

[0044] Figure 4 1 is a flow chart of a mold processing precision control method provided by an embodiment of the present application;

[0045] Figure 5 is a schematic diagram of a UG quick key query interface provided by an embodiment of the present application;

[0046] Figure 6 is a schematic diagram of the relationship between a feature surface and a tolerance provided by another embodiment of the present application;

[0047] Figure 7 This is a schematic diagram of the positions of the laser sensor and the temperature sensor provided in another embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, each embodiment of the present application will be described in detail below with reference to the accompanying drawings. However, it will be understood by those skilled in the art that in each embodiment of the present application, many technical details are proposed to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical solutions claimed in the present application can be implemented. The division of the following embodiments is for convenience of description and should not constitute any limitation on the specific implementation of the present application. The various embodiments can be combined and referenced with each other under the premise of no contradiction.

[0049] In order to facilitate understanding of the embodiments of the present application, relevant content about the mold processing precision control method is first introduced here.

[0050] Mold processing refers to the process of manufacturing forming tools (such as stamping molds, injection molds, etc.) and blanking tools. It is usually composed of an upper mold and a lower mold. The material is formed by a press and is widely used in electronic connectors, automotive parts and other fields.

[0051] Some mold manufacturing techniques rely on manual experience and apply a uniform machining standard to all surface features of the component being machined. However, these machining methods cannot accommodate the varying precision requirements of the component's surface features, resulting in wasted resources in high-precision areas and a lack of guaranteed machining accuracy.

[0052] In order to solve the technical problem that the above-mentioned existing processing method cannot process the characteristic surfaces according to the different precision requirements on the mold, which easily leads to waste of resources in high-precision areas and its processing accuracy cannot be guaranteed, the present invention proposes a mold processing accuracy control method. The implementation details of the mold processing accuracy control method of this embodiment are specifically described below. The following content is only the implementation details provided for the convenience of understanding and is not necessary for the implementation of this solution.

[0053] Example 1:

[0054] The mold processing precision control method of this embodiment can be applied to electronic devices with communication, computing and data storage capabilities. The specific process can be as follows: Figure 1 As shown, including:

[0055] Step 101 : for a plurality of preset feature surfaces to be machined of a component to be machined, obtain the tolerance and initial programming allowance corresponding to each feature surface, wherein the tolerance and / or initial programming allowance of each feature surface are not completely the same.

[0056] Specifically, the parts to be machined have various types of feature surfaces, such as air gaps, parting surfaces, glue points, vents, grooves, and hangers, as shown in Table 1. Each feature surface corresponds to a tolerance and initial programming allowance. Furthermore, because the machining accuracy required for each feature surface varies, the tolerances and / or initial programming allowances for each feature surface vary. The programming allowance refers to a certain amount added to the theoretical machining dimensions during machining to ensure that the machined part meets the required dimensions and quality.

[0057] Table 1 Feature surface-tolerance comparison table

[0058]

[0059] Step 102: During the processing of any feature surface, the state deviation of the feature surface is periodically detected. When the state deviation is detected to be greater than the deviation threshold, the PID algorithm is called to compensate and update the current programming margin. The larger the state deviation value, the greater the compensation amount for the current programming margin.

[0060] Specifically, during the machining process of a feature surface, the state of the feature surface is periodically monitored to determine the state deviation. The state of the feature surface includes dimensional, temperature, and stress states, which can be monitored by installed sensors. Furthermore, the state deviation refers to the difference between the actual state value and the preset standard value. If the state deviation is greater than the deviation threshold, it indicates that the machining accuracy of the feature surface of the component is poor, and the PID algorithm needs to be invoked to compensate and update the current programming allowance.

[0061] Specifically, when it is detected that the state deviation is greater than the deviation threshold, the PID algorithm is called to compensate and update the current programming margin, including:

[0062] When it is detected that the state deviation is greater than the deviation threshold, the compensation amount for the current programming margin is calculated based on the state deviation through the PID algorithm;

[0063] The compensation amount is added to the current programming margin to obtain the current programming margin after compensation.

[0064] Specifically, when it is detected that the state deviation is greater than the deviation threshold, it means that the machining accuracy of the feature surface of the component is poor. Based on the state deviation, the PID algorithm is used to calculate the compensation amount for the current programming allowance. Specifically, the PID control algorithm is used, and the relationship between the control signal is: Where, is the proportional coefficient of the PID controller, is the integral coefficient of the PID controller, is the differential coefficient of the PID controller. Based on the state deviation, the PID algorithm calculates the compensation for the current programming margin. This compensation is then added to the current programming margin to obtain the compensated current programming margin. This dynamic compensation is then applied to the current programming margin, and the feature surface is then processed again using the adjusted machining parameters, effectively improving the machining accuracy of the feature surface.

[0065] In some cases, the state deviation Δ>0.005mm is calculated by error: e(t) = set value - sensor measured value (e.g. e(t) = 0.01mm), and the integral term is calculated: = The cumulative error value over the past 30 seconds (e.g. 0.15 mm·s), calculated using the differential term: =(current deviation - deviation in the previous second) / 1s (e.g. 0.005mm / s).

[0066] Output compensation: u(t) = 0.8*0.01+0.2*0.15+0.1*0.005=0.008+0.03+0.0005=0.0385mm. The compensation is now 0.0385mm. Adding this compensation to the current programming allowance adjusts the program allowance from -0.005mm to -0.005-0.0385=-0.0435mm. It should be noted that the "-" sign indicates that the tool moves closer to the part being machined.

[0067] In some examples, the coefficients may be set as: =0.8 (compensation for tool wear), =0.2 (eliminating steady-state error), =0.1 (suppresses sudden vibration). When the deviation e(t)=0.01mm is detected, the system automatically calculates the compensation amount u(t)=0.8*0.01+0.2*(accumulated error integral)+0.1*(error change rate), and finally adjusts the margin from -0.005mm to -0.008mm.

[0068] Step 103 : Adjust the machining parameters currently used for machining the feature surface, and continue machining the feature surface by combining the compensated current programming allowance with the adjusted machining parameters.

[0069] Specifically, machining parameters refer to the parameters of the machining machine used to control the cutting tool on the mold when machining the component to be machined. These machining parameters are not necessarily the optimal machining parameters for machining the feature surface. Therefore, the machining parameters currently used to machine the feature surface need to be adjusted. In this embodiment, after calling the PID algorithm to compensate and update the current programming margin, the compensated current programming margin is obtained. This compensated current programming margin is then combined with the adjusted machining parameters to continue machining the feature surface.

[0070] In this embodiment, the tolerance and initial programming allowance corresponding to multiple preset feature surfaces to be machined on a component to be machined are obtained. During the machining of any feature surface, the state deviation of the feature surface is periodically detected. When the state deviation is detected to be greater than a deviation threshold, a PID algorithm is invoked to compensate and update the current programming allowance. Specifically, when the state deviation is detected to be greater than the deviation threshold, a compensation amount for the current programming allowance is calculated based on the state deviation using the PID algorithm. The compensation amount is then superimposed on the current programming allowance to obtain the compensated current programming allowance. The machining parameters currently used to machine the feature surface are then adjusted, and the feature surface is continued to be machined in combination with the compensated current programming allowance and the adjusted machining parameters. In this way, by machining different feature surfaces to different degrees of precision, graded precision control is achieved. Furthermore, the current programming allowance is dynamically compensated and updated using the PID algorithm, and the feature surface is then continued to be machined in combination with the adjusted machining parameters, effectively improving the machining precision of the feature surface.

[0071] In some embodiments, the method further comprises:

[0072] Constructing a mapping table containing different feature faces, and the feature identifiers and tolerances corresponding to each feature face;

[0073] Setting an initial programming margin corresponding to each feature surface, and constructing a mapping table including different feature surfaces and the initial programming margin corresponding to each feature surface;

[0074] Get the tolerance and initial programming allowance corresponding to each feature surface, including:

[0075] Based on the feature identifiers of each feature surface pre-defined in the software model library, the tolerance and initial programming allowance corresponding to each feature surface are matched from the mapping table.

[0076] Specifically, feature identifiers include colors, letters, and numbers. Different feature surfaces can be identified using different colors, letters, and numbers. In some cases, distinct colors may be preferred over letters and numbers for identifying feature surfaces. By establishing a mapping table between feature surfaces, feature identifiers, and tolerances, it is possible to quickly match feature surfaces with corresponding colors and tolerances. This means that when machining a feature surface of a certain color, the corresponding feature surface and tolerance can be quickly matched based on color.

[0077] In this embodiment, each feature surface also corresponds to an initial programming allowance. Using a pre-built mapping table of feature surfaces and initial programming allowances, the initial programming allowance corresponding to each feature surface can be quickly obtained. Before machining, the tolerance and initial programming allowance corresponding to each feature surface are matched from this pre-built mapping table based on the feature identifiers pre-defined in the software model library. This allows for rapid acquisition of the tolerance and initial programming allowance corresponding to each feature surface, effectively reducing reliance on manual experience.

[0078] In some embodiments, the state deviation of the feature surface is calculated by the following steps:

[0079] In the process of machining the feature surface, the size deviation, temperature deviation and stress deviation of the feature surface are periodically obtained;

[0080] The dimensional deviation, temperature deviation and stress deviation obtained in the same cycle are fused and calculated to obtain the state deviation.

[0081] Specifically, if Figure 7 As shown, by installing a laser sensor on the spindle side of the processing machine tool that controls the tool to monitor the actual size, the size deviation is obtained; by installing a temperature sensor on the outside of the spindle of the processing machine tool that controls the tool to monitor the actual temperature, the temperature deviation is obtained; by installing a force sensor on the fixture of the processing machine tool that controls the tool to monitor the actual clamping stress, the stress deviation is obtained; wherein the deviation is the difference between the actual value and the preset standard value.

[0082] In this embodiment, after obtaining the dimensional deviation, temperature deviation, and stress deviation of the characteristic surface, a weighted distribution is performed on the dimensional deviation, temperature deviation, and stress deviation obtained within the same cycle. For example, a 60% weighting is applied to the dimensional deviation (accuracy ±0.005mm), a 30% weighting is applied to the temperature deviation (compensation for thermal expansion), and a 10% weighting is applied to the stress deviation (detection of clamping stress). The weighted dimensional deviation, temperature deviation, and stress deviation are then fused and calculated to obtain the state deviation. The fusion formula is as follows:

[0083] ;

[0084] The fused value obtained by the above formula is the state deviation. When the state deviation is detected to be greater than the deviation threshold, the PID algorithm is called to compensate and update the current programming margin. In this way, by fusing the data transmitted by sensors in different locations, multi-sensor data fusion is achieved, making the derived state deviation more accurate.

[0085] In some embodiments, adjusting the processing parameters currently used to process the feature surface includes:

[0086] The characteristic parameters of the currently processed component and the mold used to process the component are input into a pre-built processing prediction model for prediction, and predicted processing parameters that match the characteristic parameters of the currently processed component and the mold used to process the component are obtained, and the predicted processing parameters are used as the adjusted processing parameters.

[0087] Specifically, the characteristic parameters of the currently processed component and the mold used to process the component include: the material hardness of the component to be processed, the wear of the tool on the mold, and the vibration frequency. The machining prediction model is used to output machining parameters that are more suitable for the subsequent machining of the feature surface in the current machining process than the current machining parameters. It is understood that different feature surfaces correspond to different initial machining parameters, which can be understood as theoretical machining parameters or historical machining parameters. The characteristic parameters of the currently processed component and the mold used to process the component are input into the machining prediction model for prediction, resulting in predicted machining parameters that match the characteristic parameters of the currently processed component and the mold used to process the component. These predicted machining parameters are then used as adjusted machining parameters. In this way, by dynamically adjusting the machining parameters of different feature surfaces, the adjusted machining parameters are more suitable for the feature surface in the current machining process. Further machining of the feature surface based on the adjusted machining parameters can effectively improve the machining accuracy of the feature surface.

[0088] In some embodiments, characteristic parameters of the component being processed include the material hardness of the component, characteristic parameters of the mold used to process the component include the wear and vibration frequency of the tool on the mold, and processing parameters include the spindle speed and feed speed of the processing machine tool used to control the tool;

[0089] The processing prediction model is obtained through the following steps:

[0090] Build the original model;

[0091] The characteristic parameter samples of parts in the historical processing state for multiple time periods, the characteristic parameter samples of the molds used to process the parts, and the corresponding processing parameter samples are obtained. The qualified rate of the processed products corresponding to the samples in each time period is constrained, and the reinforcement learning algorithm is used to train the original model to obtain a processing prediction model.

[0092] Specifically, by collecting characteristic parameter samples of components in a historical processing state at multiple time periods, characteristic parameter samples of the molds used to process the components, and corresponding processing parameter samples as training sample data, a reinforcement learning algorithm is used to train the original model to obtain a processing prediction model. The historical training sample data must be constrained by the qualified rate of the finished products corresponding to the samples in each time period. In other words, the characteristic parameters corresponding to the finished products with high qualified rates, the characteristic parameters of the molds, and the corresponding processing parameter samples are used to train the original model using a reinforcement learning algorithm. In this way, by training the original model with sample data constrained by the qualified rate, the prediction accuracy of the resulting processing prediction model is improved.

[0093] In some examples, the model training data includes 1,000 sets of historical machining records (including tool wear and vibration frequency, component material hardness, and the relationship between pass rate). After obtaining this historical data, the data is normalized: tool wear ranges from 0 to 0.5 mm, normalized to 0 to 1, and material hardness ranges from HRC 20 to 60, normalized to 0 to 1. When making predictions, the current values ​​are input: tool wear = 0.3 mm (normalized to 0.6), vibration frequency = 150 Hz (normalized to 0.5), and material hardness = HRC 50 (normalized to 0.75). The feed rate is calculated using the following equation: Y = 0.8 * tool wear + 0.15 * material hardness + 0.05 * vibration frequency + b (offset term). 0.8, 0.15, and 0.05 are coefficients that can be set. For example, Y = 0.8 * 0.6 + 0.15 * 0.75 + 0.05 * 0.5 = 0.48 + 0.1125 + 0.025 = 0.6175. The result is then denormalized: Y = 0.6175, which corresponds to a feed rate of 400 + (600 - 400) * 0.6175 = 523.5 mm / min. It should be noted that the spindle speed can also be predicted using the above steps.

[0094] In some examples, a training sample library is constructed, wherein the training sample library is used to store characteristic parameter samples of components, characteristic parameter samples of molds used to process the components, and corresponding processing parameter samples;

[0095] Adjust the machining parameters currently used to machine the feature surface, and combine the current programming allowance after compensation with the adjusted machining parameters to continue machining the feature surface, and also include:

[0096] The feature parameters of the component corresponding to the predicted feature surface, the feature parameters of the mold used to process the component, and the corresponding processing parameters are added to the training sample library to provide the samples required for the original model training.

[0097] In some embodiments, the method further comprises:

[0098] When it is detected that the state deviation is less than or equal to the deviation threshold, the processing parameters currently used for processing the feature surface are directly adjusted, and the feature surface is continued to be processed based on the adjusted processing parameters.

[0099] Specifically, when a state deviation is detected to be less than or equal to a deviation threshold, indicating that the machining accuracy of the component's feature surface is good, there's no need to dynamically compensate for the state deviation. Therefore, the machining parameters currently used to machine the feature surface are directly adjusted, and the feature surface continues to be machined based on the adjusted parameters. The steps for adjusting the machining parameters are the same as those used when the state deviation is greater than the deviation threshold, and will not be elaborated on here. In this way, continuing to machine the feature surface based on the adjusted parameters effectively improves the machining accuracy of the feature surface.

[0100] In some examples, the initial machining parameters may be: red area (high-precision surface): spindle speed 8000 rpm, feed rate 500 mm / min, programming allowance -0.01 mm; orange area (low-precision surface): spindle speed 3000 rpm, feed rate 1500 mm / min, programming allowance 0.0 mm. Assuming the current area is in the red area of ​​high-precision surface, when the state deviation is detected to be greater than the deviation threshold, the PID algorithm is invoked to compensate and update the current programming allowance, obtaining the compensated current programming allowance. This compensated current programming allowance is then used to replace the programming allowance of the initial machining parameters. The spindle speed and / or feed rate of the initial machining parameters are then updated using the adjusted machining parameters obtained from the machining prediction model. When the state deviation is detected to be less than or equal to the deviation threshold, the spindle speed and / or feed rate of the initial machining parameters are directly updated using the adjusted machining parameters obtained from the machining prediction model, leaving the programming allowance in the initial machining parameters unchanged.

[0101] Example 2:

[0102] like Figure 4 As shown, this embodiment provides exemplary content of the first embodiment, that is, provides an exemplary process of the mold processing precision control method, and the specific content includes:

[0103] Step 1: Feature surface classification and dynamic coding - functional surface division: As shown in Table 1, the mold is divided into 10 types of feature surfaces (avoidance, parting surface, glue position, exhaust, groove, etc.), and dynamic tolerance rules are defined (for example, for every 10 degrees Celsius increase in temperature, the cavity surface tolerance is tightened by 0.001mm). Figure 6As shown in the figure, there is a corresponding relationship between feature surfaces and tolerances. For example, for feature surfaces such as the sealing surface, the corresponding tolerance range is set (0~0.01); for feature surfaces such as the high-precision surface, the corresponding tolerance range is set (-0.01~+0.01).

[0104] UG coloring operation: Use UG / Open API to color the feature surface, and write the color ID into the model attribute library.

[0105] Step 2: UG plug-in development and real-time monitoring - plug-in function: such as Figure 5 As shown, set a shortcut key 1 for the color ID, shortcut key "Ctrl+Shift+C": After selecting the surface, you can Figure 5 The right part shows the tolerance, roughness and recommended tools (for example, the red area recommends a φ2mm carbide milling cutter).

[0106] Dynamic compensation logic:

[0107] When the state deviation Δ>0.005mm is detected, the PID formula is called to adjust the margin:

[0108] PID dynamic compensation control When the real-time state deviation of the characteristic surface exceeds the threshold:

[0109] 1) Error calculation: e(t) = set value - sensor measured value (e.g. e(t) = 0.01mm);

[0110] 2) Integral term calculation: = the cumulative error value over the past 30 seconds (e.g., 0.15 mm·s);

[0111] 3) Differential term calculation: de(t) / dt=(current error - error in the previous second) / 1s (e.g. 0.005mm / s);

[0112] 4) Output compensation: u(t)=0.8*0.01+0.2*0.15+0.1*0.005=0.008+0.03+0.0005=0.0385mm;

[0113] 5) Execute action: Adjust the program margin from -0.005mm to -0.005-0.0385=-0.0435mm.

[0114] Step 3: Matching machining execution with AI optimization-CAM strategy such as:

[0115] Red area (high-precision surface): spindle speed 8000rpm, feed 500mm / min, program allowance -0.01mm;

[0116] Orange area (low-precision surface): spindle speed 3000rpm, feed 1500mm / min, allowance 0.0mm.

[0117] AI parameter prediction: Based on historical data training model, input (HRC45), output optimal feed rate 480mm / min.

[0118] 1) Model training data: 1,000 sets of historical processing records (including the relationship between tool wear, material hardness, vibration frequency and pass rate);

[0119] 2) Feature standardization: tool wear range 0~0.5mm, normalized to 0~1, material hardness HRC20~60, normalized to 0~1;

[0120] 3) Prediction application: Input current values: tool wear = 0.3 mm (normalized to 0.6), material hardness = HRC50 (normalized to 0.75), vibration frequency = 150 Hz (normalized to 0.5);

[0121] Calculation: Y=0.8*0.6+0.15*0.75+0.05*0.5=0.48+0.1125+0.025=0.6175;

[0122] Denormalization: Y=0.6175, then the corresponding feed speed = 400+(600-400)*0.6175=523.5mm / min.

[0123] Step 4: Closed-loop feedback and self-learning - CMM data return: The three-coordinate inspection data automatically updates the tolerance mapping table. For example, if a guide surface passes the test five times in a row, the tolerance is relaxed from ±0.01mm to ±0.015mm.

[0124] When processing multi-cavity molds, the main cavity (red) is processed first and the backup cavity (yellow) is processed later, which improves resource utilization by 20%.

[0125] This approach breaks through the limitations of static color coding and forms a closed-loop technology through dynamic compensation and AI prediction. It clarifies sensor deployment, data fusion formulas, and PID parameter setting rules, making them highly implementable. This has resulted in a 35% increase in processing efficiency and a reduction in new employee training to just one week. Table 2 below provides a comparison of the actual results:

[0126] Table 2 Actual effect comparison table

[0127]

[0128] This embodiment has the following innovative features:

[0129] 1. Dynamic color coding system:

[0130] Dynamic mapping of feature surface, color, and tolerance (ID62 aqua → high-precision surface, tolerance fluctuates with temperature ±0.01mm). Technical Features: Color ID is deeply integrated with UG / CAM software, supporting real-time tolerance adjustment.

[0131] 2. Multi-sensor data fusion:

[0132] Sensor deployment: laser displacement sensor (spindle side), temperature sensor (spindle side), force sensor (fixture).

[0133] Fusion formula: ;

[0134] Parameter meaning: Laser sensor weight 60% (accuracy ±0.005mm), temperature sensor 30% (compensation for thermal expansion), force sensor 10% (detection of clamping stress);

[0135] Application scenario: When X laser = +0.01mm (out of tolerance), X temperature = +5°C (thermal expansion 0.003mm), and X force = 200N (stress deformation 0.001mm), the fusion value X = 0.6*0.01+0.3*0.003+0.1*0.001=0.0069mm, triggering the compensation mechanism.

[0136] 3. AI-assisted decision-making model:

[0137] Input features: tool wear, material hardness, real-time vibration frequency.

[0138] Predicted machining parameters Y = 0.8 * tool wear + 0.15 * material hardness + 0.05 * vibration frequency + b (bias term);

[0139] Input example: Tool wear = 0.2 mm, Material hardness = HRC45, Vibration frequency = 120 Hz. Calculation yields Y = 0.8 * 0.2 + 0.15 * 45 + 0.05 * 120 = 0.16 + 6.75 + 6 = 12.91 → Output feed rate: 480 mm / min.

[0140] The effects achieved by this embodiment include:

[0141] Precision grading control: Through color coding (e.g. red → cavity surface, tolerance ±0.01mm; colorless → avoidance, tolerance ±0.1mm), "high-precision area finishing, low-precision area roughing" is achieved, improving processing efficiency by 35%.

[0142] Dynamic tolerance compensation: An integrated laser sensor monitors dimensional deviations in real time and automatically corrects program allowances (e.g., adjusting the allowance from -0.005mm to -0.008mm) through a PID control algorithm. After compensation, the pass rate increases from 82% to 98%.

[0143] Using the PID control algorithm, the control signal is calculated as:

[0144] ;

[0145] Parameter settings: =0.8 (compensation for tool wear), =0.2 (eliminating steady-state error), =0.1 (suppresses sudden vibrations).

[0146] Application example: When the laser sensor detects a cavity surface dimensional deviation of e(t) = 0.01mm, the system automatically calculates the compensation amount u(t) = 0.80.01 + 0.2 (accumulated error integral) + 0.1 * (error change rate), ultimately adjusting the margin from -0.005mm to -0.008mm. Table 3 below is the experimental data table:

[0147] Table 3 Experimental data table

[0148]

[0149] AI parameter prediction: A deep learning model (machining prediction model) is trained based on historical data to predict the optimal spindle speed and feed rate, reducing programming time by 50%.

[0150] Example 3:

[0151] Another embodiment of the present application relates to a mold processing precision control device. The implementation details of the mold processing precision control device of this embodiment are specifically described below. The following content is only for the convenience of understanding the implementation details, and is not necessary for the implementation of this solution. The schematic diagram of the mold processing precision control device of this embodiment can be as follows: Figure 2 As shown, including:

[0152] An acquisition module 201 is configured to acquire, for a plurality of preset feature surfaces to be machined on a component to be machined, a tolerance and an initial programming allowance corresponding to each feature surface, wherein the tolerances and / or initial programming allowances of the feature surfaces are not identical;

[0153] The compensation module 202 is used to periodically detect the state deviation of any feature surface during the processing of the feature surface. When the state deviation is detected to be greater than the deviation threshold, the PID algorithm is called to compensate and update the current programming margin. The larger the state deviation value, the greater the compensation amount for the current programming margin.

[0154] The first adjustment module 203 is used to adjust the processing parameters currently used to process the feature surface, and continue processing the feature surface in combination with the compensated current programming allowance and the adjusted processing parameters.

[0155] In some embodiments, the compensation module 202 includes:

[0156] The first acquisition unit is used to periodically acquire the size deviation, temperature deviation and stress deviation of the feature surface during the process of machining the feature surface;

[0157] The fusion unit is used to perform fusion calculation on the dimensional deviation, temperature deviation and stress deviation obtained in the same cycle to obtain the state deviation.

[0158] In some embodiments, the mold processing precision control device includes:

[0159] A first construction module is used to construct a mapping table including different feature faces, and feature identifiers and tolerances corresponding to each feature face;

[0160] A second construction module is used to set an initial programming margin corresponding to each feature surface, and to construct a mapping table including different feature surfaces and the initial programming margin corresponding to each feature surface;

[0161] The acquisition module 201 is further configured to match the tolerance and initial programming margin corresponding to each feature surface from a mapping table based on the feature identifiers of each feature surface pre-defined in the software model library.

[0162] In some embodiments, the compensation module 202 further includes:

[0163] a calculation unit, configured to calculate a compensation amount for a current programming margin based on the state deviation by using a PID algorithm when it is detected that the state deviation is greater than a deviation threshold;

[0164] The superposition unit is used to superpose the compensation amount with the current programming margin to obtain the compensated current programming margin.

[0165] In some embodiments, the first adjustment module 203 is also used to input the characteristic parameters of the currently processed component and the mold used to process the component into a pre-built processing prediction model for prediction, obtain predicted processing parameters that match the characteristic parameters of the currently processed component and the mold used to process the component, and use the predicted processing parameters as the adjusted processing parameters.

[0166] In some embodiments, the mold processing precision control device further includes:

[0167] The model building module is used to build the original model; the characteristic parameter samples of the parts in the historical processing state for multiple time periods, the characteristic parameter samples of the molds used to process the parts, and the corresponding processing parameter samples are obtained, and the qualified rate of the processed products corresponding to the samples in each time period is used as a constraint. The original model is trained using a reinforcement learning algorithm to obtain a processing prediction model.

[0168] In some embodiments, the mold processing precision control device further includes:

[0169] The second adjustment module is used to directly adjust the processing parameters currently used to process the feature surface when it is detected that the state deviation is less than or equal to the deviation threshold, and continue to process the feature surface based on the adjusted processing parameters.

[0170] It is worth mentioning that all modules involved in this embodiment are logical modules. In actual applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, to highlight the innovation of this application, this embodiment does not include units that are not closely related to solving the technical problem proposed by this application. However, this does not mean that other units do not exist in this embodiment.

[0171] Example 4:

[0172] Another embodiment of the present application relates to an electronic device, such as Figure 3 As shown, it includes: at least one processor 901; and a memory 902 that is communicatively connected to the at least one processor 901; wherein the memory 902 stores instructions that can be executed by the at least one processor 901, and the instructions are executed by the at least one processor 901 so that the at least one processor 901 can execute the mold processing accuracy control method in the above-mentioned embodiments.

[0173] The memory and processor are connected using a bus, which can include any number of interconnected buses and bridges. The bus connects various circuits of one or more processors and memories. The bus can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits. These are all well known in the art and are therefore not described further herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be a single component or multiple components, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by the processor is transmitted over a wireless medium via an antenna. Furthermore, the antenna receives data and transmits it to the processor.

[0174] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory can be used to store data used by the processor when performing operations.

[0175] Embodiment 5:

[0176] Another embodiment of the present application relates to a computer-readable storage medium storing a computer program, which implements the above method embodiment when executed by a processor.

[0177] That is, those skilled in the art will understand that all or part of the steps in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a program. The program is stored in a storage medium and includes a number of instructions for causing a device (which may be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps in the methods described in the various embodiments of this application. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0178] Those skilled in the art will appreciate that the above embodiments are specific embodiments for implementing the present application, and that in actual applications, various changes may be made thereto in form and detail without departing from the spirit and scope of the present application.

Claims

1. A mold processing precision control method, characterized in that: include: For a plurality of preset feature surfaces to be machined of a component to be machined, obtaining a tolerance and an initial programming allowance corresponding to each of the feature surfaces, wherein the tolerances and / or initial programming allowances of the feature surfaces are not completely the same; During the processing of any of the feature surfaces, the state deviation of the feature surface is periodically detected. When it is detected that the state deviation is greater than a deviation threshold, a PID algorithm is called to compensate and update the current programming margin. The larger the value of the state deviation is, the greater the compensation amount for the current programming margin is. Adjusting the machining parameters currently used for machining the characteristic surface, and continuing to machine the characteristic surface in combination with the compensated current programming allowance and the adjusted machining parameters; When it is detected that the state deviation is greater than the deviation threshold, calling the PID algorithm to compensate and update the current programming margin includes: When it is detected that the state deviation is greater than the deviation threshold, calculating the compensation amount for the current programming margin based on the state deviation by using the PID algorithm; The compensation amount is added to the current programming margin to obtain the compensated current programming margin.

2. The mold processing accuracy control method according to claim 1, characterized in that: The method further comprises: Constructing a mapping table containing different feature faces, and the feature identifiers and tolerances corresponding to each feature face; Setting an initial programming margin corresponding to each of the characteristic surfaces, and constructing a mapping table including different characteristic surfaces and the initial programming margin corresponding to each characteristic surface; The obtaining of the tolerance and initial programming margin corresponding to each of the feature surfaces includes: Based on the feature identifiers of the feature surfaces pre-defined in the software model library, the tolerance and initial programming margin corresponding to each feature surface are matched from the mapping table.

3. The mold processing accuracy control method according to claim 1, characterized in that: The state deviation of the characteristic surface is calculated by the following steps: In the process of machining the characteristic surface, periodically obtaining the size deviation, temperature deviation and stress deviation of the characteristic surface; The size deviation, the temperature deviation, and the stress deviation obtained in the same cycle are fused and calculated to obtain the state deviation.

4. The mold processing accuracy control method according to claim 1, characterized in that: The adjusting of the processing parameters currently used for processing the feature surface includes: The characteristic parameters of the currently processed component and the mold used to process the component are input into a pre-built processing prediction model for prediction, and predicted processing parameters that match the characteristic parameters of the currently processed component and the mold used to process the component are obtained, and the predicted processing parameters are used as the adjusted processing parameters.

5. The mold processing accuracy control method according to claim 4, characterized in that: The characteristic parameters of the currently processed component include the material hardness of the component, the characteristic parameters of the mold used to process the component include the wear and vibration frequency of the tool on the mold, and the processing parameters include the spindle speed and feed speed of the processing machine tool used to control the tool; The processing prediction model is obtained by the following steps: Build the original model; The characteristic parameter samples of the component in the historical processing state for multiple time periods, the characteristic parameter samples of the mold used to process the component, and the corresponding processing parameter samples are obtained. The qualified rate of the processed products corresponding to the samples in each time period is constrained, and the reinforcement learning algorithm is used to train the original model to obtain the processing prediction model.

6. The mold processing accuracy control method according to claim 1, characterized in that: The method further comprises: When it is detected that the state deviation is less than or equal to the deviation threshold, the processing parameters currently used for processing the feature surface are directly adjusted, and the feature surface is continued to be processed based on the adjusted processing parameters.

7. A mold processing precision control device, characterized in that: include: An acquisition module is used to acquire, for a plurality of preset characteristic surfaces to be machined of a component to be machined, a tolerance and an initial programming allowance corresponding to each of the characteristic surfaces, wherein the tolerances and / or initial programming allowances of the characteristic surfaces are not completely the same; A compensation module is configured to periodically detect a state deviation of any of the feature surfaces during machining, and when it is detected that the state deviation is greater than a deviation threshold, invoke a PID algorithm to compensate and update the current programming margin, wherein the greater the value of the state deviation, the greater the compensation amount for the current programming margin. The compensation module includes: a calculation unit configured to calculate a compensation amount for the current programming margin based on the state deviation using a PID algorithm when it is detected that the state deviation is greater than the deviation threshold; and a superposition unit configured to superpose the compensation amount with the current programming margin to obtain the compensated current programming margin; The first adjustment module is used to adjust the processing parameters currently used to process the characteristic surface, and continue to process the characteristic surface in combination with the compensated current programming allowance and the adjusted processing parameters.

8. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the mold processing accuracy control method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the mold processing accuracy control method according to any one of claims 1 to 6 is implemented.

Images