Dynamic correction method, system and equipment for mold processing deviation based on real-time monitoring

Abstract

The present application provides a dynamic correction method, system and device for mold processing deviation based on real-time monitoring, which relates to the technical field of industrial processing control. The method includes: reading a target processing plan of a target mold; performing collaborative analysis on target design parameters and target process requirements to obtain a real-time workpiece preset model; dynamically monitoring the processing process of the target mold; constructing a real-time workpiece actual model according to the real-time state parameters of the target mold; comparing the real-time workpiece actual model with the real-time workpiece preset model to obtain a model comparison deviation; performing correction optimization to obtain an optimal correction strategy; and performing dynamic processing correction on the target mold. By means of the present application, the technical problem that it is difficult to accurately identify dynamic errors due to the difficulty of the preset model in timely capturing and correcting the dynamic changes generated in the processing process, thereby affecting the processing accuracy and quality of the mold is solved. By identifying the dynamic deviation and determining the optimal correction strategy, the processing accuracy and quality of the mold are improved.

Description

Technical Field

[0001] The present application relates to the technical field of industrial processing control, and particularly to a dynamic correction method, system and equipment for die processing deviation based on real-time monitoring. Background Art

[0002] During the die processing, due to the changes in processing environment, machine tool state, material properties and tool conditions, the errors in die processing are dynamic and variable, and traditional processing modes often have difficulty in capturing these changes in a timely manner. In order to ensure the high precision and high quality of die processing, currently, pre-compensation is usually carried out by establishing a static error model (such as geometric error, thermal error, tool wear compensation, etc.) before processing, but it is unable to cope with the real-time error changes during processing. Using the on-line monitoring data during processing to correct the error in real time, but the response speed is poor and it is difficult to achieve real-time compensation. Detecting the error after processing and then performing secondary processing or manual correction, but the cost is high and it is not suitable for mass production. During the processing, affected by various factors such as environmental temperature, tool wear, vibration, workpiece material properties, etc., the actual state will change in real time, and the traditional pre-set compensation model cannot cover these instantaneous dynamic factors, resulting in a large deviation between the design parameters and the actual state, making it difficult to accurately identify the dynamic error, affecting the control of the machine tool fieldbus, and thus affecting the processing precision and quality of the die.

[0003] In summary, there is a technical problem in the prior art that due to the difficulty of the pre-set model in capturing and correcting the dynamic changes generated during the processing in a timely manner, it is difficult to accurately identify the dynamic error, thus affecting the processing precision and quality of the die. Summary of the Invention

[0004] The purpose of the present application is to provide a dynamic correction method, system and equipment for die processing deviation based on real-time monitoring, so as to solve the technical problem in the prior art that due to the difficulty of the pre-set model in capturing and correcting the dynamic changes generated during the processing in a timely manner, it is difficult to accurately identify the dynamic error, thus affecting the processing precision and quality of the die.

[0005] In view of the above problems, the present application provides a dynamic correction method, system and equipment for die processing deviation based on real-time monitoring.

[0006] In a first aspect, the present application provides a dynamic correction method for mold processing deviation based on real-time monitoring. The dynamic correction method for mold processing deviation based on real-time monitoring is implemented through a dynamic correction system for mold processing deviation based on real-time monitoring. Among them, the dynamic correction method for mold processing deviation based on real-time monitoring includes: reading a target processing plan of a target mold, where the target processing plan includes target design parameters and target process requirements; performing collaborative analysis on the target design parameters and the target process requirements to obtain a real-time workpiece preset model; dynamically monitoring the processing process of the target mold through a sensor network to obtain real-time sensing information; analyzing the real-time sensing information to obtain real-time state parameters of the target mold, and constructing a real-time workpiece actual model according to the real-time state parameters; comparing the real-time workpiece actual model with the real-time workpiece preset model to obtain a model comparison deviation; performing correction optimization with the model comparison deviation as an optimization constraint to obtain an optimal correction strategy; and dynamically correcting the processing of the target mold according to the optimal correction strategy.

[0007] Optionally, an initial geometric model is constructed according to the design shape, design interior, and design relative position in the target design parameters; the target process requirements are integrated into the initial geometric model to obtain an initial model; the real-time moment is obtained, and the initial model is analyzed for the processing process in combination with the real-time moment to obtain the model at the real-time moment, denoted as the real-time workpiece preset model.

[0008] Optionally, dynamic processing monitoring is performed on the target mold through a displacement sensor in the sensor network to obtain real-time displacement; dynamic processing monitoring is performed on the target mold through a strain gauge in the sensor network to obtain real-time strain; dynamic processing monitoring is performed on the target mold through a laser rangefinder in the sensor network to obtain real-time processing accuracy; and the real-time sensing information is composed based on the real-time displacement, the strain, and the real-time processing accuracy.

[0009] Optionally, the real-time sensing information is standardized to obtain real-time standard sensing information; a predetermined sensing feature index is introduced and the real-time standard sensing information is traversed and extracted to obtain real-time standard feature parameters; and the real-time standard feature parameters are rendered and fused into the initial model of the target mold to obtain the real-time workpiece actual model.

[0010] Optionally, the predetermined sensing feature index includes a displacement sensing feature index, a strain sensing feature index, and a processing accuracy sensing feature index.

[0011] Optionally, an evaluation function for model size deviation is introduced to evaluate and analyze the size deviation between the actual model of the real-time workpiece and the preset model of the real-time workpiece, so as to obtain the model size deviation; an evaluation function for model shape deviation is introduced to evaluate and analyze the shape deviation between the actual model of the real-time workpiece and the preset model of the real-time workpiece, so as to obtain the model shape deviation; an evaluation function for model position deviation is introduced to evaluate and analyze the position deviation between the actual model of the real-time workpiece and the preset model of the real-time workpiece, so as to obtain the model position deviation; the mean value of the model size deviation, the model shape deviation and the model position deviation is taken as the model comparison deviation; wherein, the formula of the model size deviation evaluation function is as follows: ; the formula of the model shape deviation evaluation function is as follows: ; the formula of the model position deviation evaluation function is as follows: ; wherein, 、 and respectively represent the model size deviation, the model shape deviation and the model position deviation, 、 and respectively represent the size, shape and position of the actual model of the real-time workpiece at the th model part, 、 and respectively represent the size, shape and position of the preset model of the real-time workpiece at the th model part, represents the total number of model parts for comparison.

[0012] Optionally, a correction optimization space is established with the target process requirements as the constraint, and any process plan in the correction optimization space is randomly extracted, wherein the any process plan is different from the real-time process plan of the target mold; based on the any process plan, the actual model of the real-time workpiece is simulated and corrected, and any correction data is recorded; a predetermined correction evaluation index is read, and based on the predetermined correction evaluation index, the any correction data is matched and extracted to obtain any correction evaluation parameters; the any correction evaluation parameters after normalization processing are subjected to mutation weighted calculation to obtain any correction fitness; taking the maximum fitness value of the any correction fitness as the target, iterative optimization is performed to obtain the optimal correction process plan, which is denoted as the optimal correction strategy.

[0013] Optionally, the predetermined correction evaluation indexes include correction accuracy, correction quality, correction performance and correction stability.

[0014] Second aspect, the present application also provides a dynamic correction system for mold processing deviation based on real-time monitoring, which is used to execute the dynamic correction method for mold processing deviation based on real-time monitoring as described in the first aspect. Among them, the dynamic correction system for mold processing deviation based on real-time monitoring includes: a pre-plan reading module, which is used to read the target processing pre-plan of the target mold, where the target processing pre-plan includes target design parameters and target process requirements; a collaborative analysis module, which is used to perform collaborative analysis on the target design parameters and the target process requirements to obtain a real-time workpiece preset model; a processing monitoring module, which is used to dynamically monitor the processing process of the target mold through a sensor network to obtain real-time sensing information; a model construction module, which is used to analyze the real-time sensing information to obtain the real-time state parameters of the target mold, and construct a real-time workpiece actual model according to the real-time state parameters; a model deviation comparison module, which is used to compare the real-time workpiece actual model with the real-time workpiece preset model to obtain a model comparison deviation; a strategy optimization module, which is used to perform correction optimization with the model comparison deviation as the optimization constraint to obtain an optimal correction strategy; a processing correction module, which is used to perform dynamic processing correction on the target mold according to the optimal correction strategy.

[0015] Third aspect, the present application also provides an electronic device, including: at least one processor; 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 so that the at least one processor can execute the steps of the dynamic correction method for mold processing deviation based on real-time monitoring as described in any one of the above first aspects.

[0016] One or more technical solutions provided in the present application have at least the following beneficial effects:

[0017] By reading the target processing plan of the target mold, where the target processing plan includes target design parameters and target process requirements; performing collaborative analysis on the target design parameters and the target process requirements to obtain a real-time workpiece preset model; dynamically monitoring the processing process of the target mold through a sensor network to obtain real-time sensing information; analyzing the real-time sensing information to obtain the real-time state parameters of the target mold, and constructing a real-time workpiece actual model based on the real-time state parameters; comparing the real-time workpiece actual model with the real-time workpiece preset model to obtain a model comparison deviation; performing correction optimization with the model comparison deviation as the optimization constraint to obtain an optimal correction strategy; and performing dynamic processing correction on the target mold according to the optimal correction strategy. That is to say, by obtaining the target design parameters and target process requirements through the processing plan, constructing a real-time workpiece preset model, dynamically monitoring the mold processing process and constructing a real-time workpiece actual model, comparing the preset model with the actual model, performing optimization based on the deviation, determining the optimal correction plan to correct the mold processing process, and adjusting the processing parameters in real time through the machine tool fieldbus control system, the accuracy and quality of mold processing are improved, thereby improving production efficiency.

[0018] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically illustrates the specific embodiments of the present application. It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings described below are only exemplary, and for those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0020] Figure 1 It is a schematic flow chart of the method for dynamically correcting the mold processing deviation based on real-time monitoring of the present application;

[0021] Figure 2 It is a schematic structural diagram of the system for dynamically correcting the mold processing deviation based on real-time monitoring of the present application;

[0022] Figure 3 It is a schematic structural diagram of an exemplary electronic device of the present application.

[0023] Explanation of the accompanying drawings: plan reading module 11, collaborative analysis module 12, processing monitoring module 13, model building module 14, model deviation comparison module 15, strategy optimization module 16, processing correction module 17, bus 300, receiver 301, processor 302, transmitter 303, memory 304, bus interface 305. DETAILED DESCRIPTION

[0024] This application solves the technical problem in the prior art that it is difficult to accurately identify dynamic errors, thereby affecting the processing accuracy and quality of the mold, by providing a dynamic correction method, system and equipment for mold processing deviation based on real-time monitoring. The preset model is difficult to capture and correct the dynamic changes generated during the processing in a timely manner, which makes it difficult to accurately identify dynamic errors, thereby affecting the processing accuracy and quality of the mold. The target design parameters and target process requirements are obtained through the processing plan, and a real-time workpiece preset model is constructed. The mold processing process is dynamically monitored and a real-time workpiece actual model is constructed. The preset model is compared with the actual model, and the optimization is performed according to the deviation. The optimal correction plan is determined to correct the processing process of the target mold. The processing parameters are adjusted in real time through the machine tool field bus control system, which improves the accuracy and quality of mold processing, thereby improving production efficiency.

[0025] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0026] For example, please refer to the attached Figure 1 The present application provides a mold processing deviation dynamic correction method based on real-time monitoring, wherein the mold processing deviation dynamic correction method based on real-time monitoring is executed by a mold processing deviation dynamic correction system based on real-time monitoring, and the mold processing deviation dynamic correction method based on real-time monitoring specifically includes the following steps:

[0027] S100: Reading a target processing plan of a target mold, wherein the target processing plan includes target design parameters and target process requirements.

[0028] Specifically, extract the target machining plan file of the target mold from a pre-stored database or file, and read the machining information of the target mold from it, including target design parameters and target process requirements. The target machining plan is usually a machining plan and scheme formulated for the target mold, containing a detailed plan for the entire machining process. The process steps, machining sequence, and technical requirements at each stage will be clearly defined in the plan. The target mold is the specific mold to be machined. The target design parameters are data such as the dimensions, geometric accuracy, and material requirements required during the design of the mold, including the external structure, internal structure, relative position, etc. The target process requirements are the technical requirements and process indicators that must be met during the mold machining process, such as cutting speed, feed rate, tool path, cooling method, etc. For example, in the machining plan of a certain mold, the target design parameters are recorded as the mold cavity size being 150.0 mm × 200.0 mm, with an allowable tolerance of ±0.02 mm; the target process requirements include a spindle speed of 1200 revolutions per minute, a feed rate of 0.05 mm per tooth, and cooling with a coolant, etc. Complete data reading within 5 milliseconds through the machine tool fieldbus, ensuring that the data accuracy error is less than 0.01 mm. At the same time, transmit the read data to the machine tool fieldbus control system for subsequent tool path planning and machining parameter setting. By reading the target design parameters and process requirements in the target mold machining plan, accurate acquisition and automatic transmission of information are achieved.

[0029] S200: Conduct collaborative analysis on the target design parameters and the target process requirements to obtain a real-time workpiece preset model.

[0030] Furthermore, S200 of this application includes:

[0031] Construct an initial geometric model according to the design outer shape, design internal part, and design relative position in the target design parameters; integrate the target process requirements into the initial geometric model to obtain an initial model; obtain the real-time moment, and combine the real-time moment to conduct a machining process analysis on the initial model to obtain the model at the real-time moment, denoted as the real-time workpiece preset model.

[0032] Specifically, according to the designed outer shape, internal design, and relative position in the target design parameters, an initial geometric model is constructed through CAD software, which reflects the basic shape and structure of the mold. The designed outer shape is the external contour and dimensions of the mold. For example, for an injection mold, it refers to the overall contour of the cavity, the curve of the mold opening surface, and external dimensions, such as a circular cavity with a diameter of 150.0 mm. The internal design is the internal structure and features of the mold, including internal grooves, cooling channels, gate positions, etc. For example, a mold contains an internal cavity with a diameter of 140.0 mm and a mold wall structure with a thickness of 5.0 mm. The relative position design is the spatial relationship and positioning of each component of the mold (such as the outer shape, internal structure, cooling channels, etc.) in the overall mold. For example, the distance, angle, and arrangement of the cooling channel relative to the mold cavity.

[0033] Integrate the target process requirements (such as machining accuracy, surface roughness, spindle speed, feed rate, cutting depth, coolant flow rate, etc.) into the initial geometric model, and associate each machining area of the mold with its corresponding process requirements to form an initial model containing process parameters, which not only reflects the geometric features of the mold but also includes the process parameters during the machining process.

[0034] Obtain the real-time moment, that is, the time node in the current machining process, and combine the real-time data at the current time node to perform a machining process analysis on the initial model, considering the machining progress and status of the mold at the current time point, so as to obtain a real-time workpiece preset model, that is, a model that reflects the geometric features of the workpiece in the current state after the machining process analysis. By constructing the initial geometric model and integrating it with the process requirements, the accuracy and efficiency of the machining process can be ensured. Combining the real-time moment for machining process analysis can predict possible problems such as deformation and stress concentration during the machining process, and accurately reflect the dynamic changes during the machining process, such as thermal expansion, vibration, and tool wear.

[0035] S300: Dynamically monitor the machining process of the target mold through a sensor network to obtain real-time sensing information.

[0036] Furthermore, S300 of this application includes:

[0037] Dynamically monitor the target mold through the displacement sensor in the sensor network to obtain real-time displacement; dynamically monitor the target mold through the strain gauge in the sensor network to obtain real-time strain; dynamically monitor the target mold through the laser rangefinder in the sensor network to obtain real-time machining accuracy; and form the real-time sensing information based on the real-time displacement, the strain, and the real-time machining accuracy.

[0038] Specifically, the processing process of the target mold is dynamically monitored through a sensor network, which is a system composed of multiple sensors for collecting and transmitting various information about the target mold. The sensor network includes displacement sensors, strain gauges, laser rangefinders, etc. Among them, the displacement sensor is used to detect the minute displacement changes generated on the surface of the workpiece or mold during the processing; the strain gauge is a commonly used stress and strain detection component. By attaching it to the key parts of the mold, it can monitor the minute deformations caused by mechanical loads or temperature changes in real time. The laser rangefinder scans the surface of the workpiece with a laser beam to obtain processing accuracy information. Based on laser reflection ranging, it can measure the size and surface profile of the mold with extremely high accuracy (usually within 0.005 mm), monitor the size changes of the mold in real time, and verify whether the processing accuracy meets the design requirements.

[0039] Displacement sensors (such as laser displacement sensors) are installed in various key processing areas to monitor the minute deformations of the mold. The strain gauges are attached to the key stress-bearing parts of the mold, and the strain borne by the mold during processing is quantified by detecting the resistance change of the metal foil. For example, during the actual processing, the strain detected by the strain gauge in a certain area is 120 microstrain (με) in real time. The laser rangefinder obtains processing accuracy information by performing high-precision measurements on the surface of the mold, thereby determining the processing accuracy deviation and reflecting whether the current processing state conforms to the design expectation.

[0040] The real-time displacement, real-time strain, and real-time processing accuracy data obtained by each sensor are processed to form real-time sensing information, which reflects the dynamic state of the mold during the processing. For example, the real-time sensing information monitored for a certain mold includes a real-time displacement of 0.012 mm, a real-time strain of 120 microstrain, and a real-time processing accuracy deviation of ±0.005 mm. Through the combined application of displacement sensors, strain gauges, and laser rangefinders in the sensor network, real-time dynamic monitoring of the target mold during the processing is achieved, and high-precision real-time sensing information is formed.

[0041] S400: Analyze the real-time sensing information to obtain the real-time state parameters of the target mold, and construct a real-time actual workpiece model based on the real-time state parameters.

[0042] Furthermore, S400 of the present application includes:

[0043] Perform standardization processing on the real-time sensing information to obtain real-time standard sensing information; introduce predetermined sensing characteristic indicators and traverse and extract the real-time standard sensing information to obtain real-time standard characteristic parameters; render and fuse the real-time standard characteristic parameters into the initial model of the target mold to obtain the real-time actual workpiece model.

[0044] The predetermined sensing feature indicators include displacement sensing feature indicators, strain sensing feature indicators, and machining accuracy sensing feature indicators.

[0045] Specifically, preprocess the real-time sensing information to handle outliers, missing values, etc. Since the acquisition accuracies, times, and frequencies of each sensor are different, standardize the preprocessed real-time sensing information to map data from different sources and with different dimensions to a unified scale or range, making them comparable. Use a normalization algorithm (such as min-max normalization or Z-score normalization) to standardize the real-time sensing information to obtain real-time standard sensing information under a unified scale. For example, in a machining experiment, the original displacement data is 0.012 mm, which is mapped to 0.75 after normalization (the normalization interval is 0 to 1), while the strain data is standardized to 0.80 from 120 microstrains, and the machining accuracy data (such as a dimensional deviation of 0.004 mm) is standardized to 0.65 after normalization. Real-time standard sensing information refers to the sensing data after standardization, which has unified data such as displacement, strain, and machining accuracy to a standard scale, thus providing a comparable and stable data basis for subsequent feature extraction.

[0046] The predetermined sensing feature indicators are key data indicators determined according to the target machining plan of the mold, and are used to extract key features from the sensing information, including displacement sensing feature indicators, strain sensing feature indicators, and machining accuracy sensing feature indicators. The displacement sensing feature indicators are specific parameters used to describe the data of displacement sensors, such as maximum displacement, average displacement, displacement change rate, etc.; the strain sensing feature indicators are specific parameters used to describe the data of strain gauges, such as maximum strain, average strain, etc.; the machining accuracy sensing feature indicators are specific parameters used to describe the data of laser rangefinders, such as maximum deviation, average deviation, etc.

[0047] Through the predetermined sensing feature indicators, traverse and extract the standardized sensing information to extract the key data that meets the predetermined feature indicators, and form real-time standard feature parameters that describe the current state. These parameters can accurately describe the key states of the mold during the machining process, such as micro-displacement, strain, and dimensional deviation during the machining process.

[0048] The real-time standard feature parameters are integrated into the original design model in a visual or numerical form through CAD software. The real-time standard feature parameters are integrated with the initial mold of the target mold, and the real-time sensor data is superimposed as a dynamic input on the initial model pre-generated in the CAD / CAM system. For example, if a mold originally designed with a size of 150.0 mm is detected with local displacement and thermal expansion at a certain processing stage, after fusion, the local area may be updated to 150.02 mm in the model, showing the deviation under the actual processing state. The rendered model is displayed in real time on the monitoring terminal through the machine tool fieldbus control system, and the dynamically updated data is intuitively presented to the operator using high-resolution industrial display screens and data visualization tools.

[0049] By integrating real-time sensor information into the model, the real-time workpiece actual model obtained can more realistically reflect the actual state of the mold, improve the accuracy of the model, and help to promptly discover and solve processing problems, thereby improving the quality and production efficiency of the mold.

[0050] S500: Compare the real-time workpiece actual model with the real-time workpiece preset model to obtain a model comparison deviation.

[0051] Furthermore, the present application S500 includes:

[0052] A model size deviation evaluation function is introduced to evaluate and analyze the size deviation of the real-time workpiece actual model and the real-time workpiece preset model to obtain a model size deviation; a model shape deviation evaluation function is introduced to evaluate and analyze the shape deviation of the real-time workpiece actual model and the real-time workpiece preset model to obtain a model shape deviation; a model position deviation evaluation function is introduced to evaluate and analyze the position deviation of the real-time workpiece actual model and the real-time workpiece preset model to obtain a model position deviation; the average of the model size deviation, the model shape deviation and the model position deviation is taken as the model comparison deviation; wherein the formula of the model size deviation evaluation function is as follows: ; The formula of the model shape deviation evaluation function is as follows: ; The formula of the model position deviation evaluation function is as follows: ;in, , and They represent the model size deviation, model shape deviation and model position deviation respectively. , and Respectively represent the actual model of the real-time workpiece in The size, shape and position of each model part, , and respectively represent the dimensions, shapes, and positions of the real-time workpiece preset model at the th model part, represents the total number of model parts for comparison.

[0053] Specifically, the model dimension deviation evaluation function is used to compare the dimensional differences between two models (the real-time workpiece actual model and the real-time workpiece preset model). The machine tool fieldbus control system obtains the real-time workpiece preset model of the target mold, collects the actual dimensional data after processing in real time through sensors, determines the real-time workpiece actual model, calculates the absolute deviation of each key dimension, sums up all the deviation values, and then divides by the sum of all preset dimensions to obtain a normalized dimension deviation index. The formula for the model dimension deviation evaluation function is as follows: , where, is the dimension of the real-time workpiece actual model at the th model part, is the dimension of the real-time workpiece preset model at the th model part, and n is the total number of model parts for comparison, which is the total number of key dimensions here.

[0054] The model shape deviation evaluation function is a function for comparing and analyzing the geometric shapes of two models. It not only compares the dimensions of each part but also considers differences in aspects such as curves, angles, and edge contours. Shape deviation not only reflects changes in local dimensions but also inconsistencies in geometric characteristics such as surface curvature and edge smoothness. Select several representative sampling points on the model surface. For each sampling point, record its three-dimensional coordinates in the preset model and the corresponding real-time three-dimensional coordinates in the actual model, and use the model shape deviation evaluation function to calculate the shape deviation. The formula for the model shape deviation evaluation function is as follows: , where, is the shape of the real-time workpiece actual model at the th model part, is the shape of the real-time workpiece preset model at the th model part, and n is the total number of model parts for comparison, which is the total number of sampling points here.

[0055] The model position deviation evaluation function is used to evaluate the differences in spatial positioning between two models, mainly focusing on the relative position changes of the main features in three-dimensional space. By calculating the overall offset degree of the real-time workpiece actual model and the real-time workpiece preset model in spatial position, different from dimensional deviation and shape deviation, position deviation focuses on the global movement of the overall workpiece in the three-dimensional coordinate system rather than the changes in local morphology. The model position deviation evaluation function calculates the Euclidean distance difference between the actually measured position and the preset design position, and performs normalization processing to obtain a dimensionless deviation index. During a certain mold processing, n key points (such as the four reference corners + the centroid of the workpiece) are selected, and their three-dimensional coordinates are measured in the actual model and the preset model respectively. The model position deviation evaluation function is used to calculate the position deviation. The formula of the model position deviation evaluation function is as follows: , where, represents the position of the real-time workpiece actual model at the th model part, represents the position of the real-time workpiece preset model at the th model part, represents the total number of model parts for comparison, which is the number of reference points here.

[0056] After comprehensively averaging the above three deviation indexes (dimensional, shape, and position deviation), the model comparison deviation is obtained, which reflects the overall difference between the actual processing state and the preset design state.

[0057] Exemplarily, after comparing the real-time workpiece actual model and the real-time workpiece preset model of a certain mold, the model dimensional deviation is shown in Table 1, the model shape deviation is shown in Table 2, the model position deviation is shown in Table 3, and the model comparison deviation is shown in Table 4.

[0058] Table 1 Model Dimensional Deviation

[0059] Number Preset Size (mm) Actual Size (mm) Absolute Deviation (mm) 1 150.000 150.015 0.015 2 75.000 75.005 0.005 3 50.000 50.010 0.010 Total 275.000 0.030

[0060] According to Table 1, the model dimensional deviation calculated by the model dimensional deviation evaluation function is 0.0109%.

[0061] Table 2 Model Shape Deviation

[0062] Sampling Point Preset Coordinate Actual Coordinate Distance Deviation 1 (100.0,100.0,50.0) (100.2,100.1,50.0) 0.224 2 (120.0,80.0,45.0) (120.1,80.1,45.0) 0.141 3 (130.0,90.0,55.0) (130.0,90.2,55.1) 0.224 4 (110.0,95.0,60.0) (110.2,95.1,60.0) 0.224 5 (115.0,85.0,52.0) (115.1,85.0,52.2) 0.100 Total 0.913

[0063] According to Table 2, the model shape deviation calculated by the model shape deviation evaluation function is 0.1174%.

[0064] Table 3 Model Position Deviation

[0065] Key Point Preset Coordinate Actual Coordinate Distance Deviation A (100.0,100.0,50.0) (100.5,100.2,50.1) 0.538 B (120.0,80.0,45.0) (120.3,80.0,44.9) 0.316 C (130.0,90.0,55.0) (130.1,90.2,55.2) 0.245 D (110.0,95.0,60.0) (110.4,95.3,60.1) 0.502 E (115.0,85.0,52.0) (115.2,85.1,52.1) 0.244 Total 1.845

[0066] According to Table 3, the model position deviation calculated by the model position deviation evaluation function is 0.237%.

[0067] Table 4 Model comparison deviation

[0068] Deviation Type Evaluation Value (Normalized Ratio) Percentage Size Deviation 0.000109 0.0109% Shape Deviation 0.001174 0.1174% Position Deviation 0.00237 0.237% Comprehensive Deviation 0.001217 0.1217%

[0069] By introducing an evaluation function to conduct a detailed deviation analysis on the real-time workpiece actual model and the real-time workpiece preset model, various deviations in the machining process can be accurately quantified. It can not only identify specific problems in dimensions, shapes, and positions but also provide a comprehensive deviation evaluation by calculating the model comparison deviation.

[0070] S600: Perform correction optimization with the model comparison deviation as the optimization constraint to obtain the optimal correction strategy.

[0071] Furthermore, S600 of this application includes:

[0072] Establish a correction optimization space with the target process requirements as the constraint, and randomly extract any process plan in the correction optimization space, where any process plan is different from the real-time process plan of the target mold; perform simulation correction on the real-time workpiece actual model based on any process plan and record any correction data; read the predetermined correction evaluation indicators, and perform matching extraction on any correction data based on the predetermined correction evaluation indicators to obtain any correction evaluation parameters; perform mutation weighted calculation on the normalized any correction evaluation parameters to obtain any correction fitness; perform iterative optimization with the maximum fitness value of any correction fitness as the goal to obtain the optimal correction process plan, which is denoted as the optimal correction strategy.

[0073] The predetermined correction evaluation indicators include correction accuracy, correction quality, correction performance, and correction stability.

[0074] Specifically, take the target process requirements (such as cutting parameters, tool paths, and compensation ranges) in the target machining plan as constraints, define the possible range of correction parameters, and establish a multi-dimensional process parameter space. The correction optimization space is a set of alternative correction plans established under the constraints of the target process requirements, aiming at the possible dynamic errors or deviations in the machining process, and includes different combinations of process parameters, tool compensation plans, and path adjustment strategies that all meet the target process requirements.

[0075] Randomly select a solution in the corrected optimization space as an arbitrary process plan, which needs to be different from the real-time process plan of the current target die. Apply the arbitrary process plan to the real-time workpiece actual model through CAD software, simulate the correction process, and record the correction results after simulation, including data such as the correction errors of dimensions, shapes, positions, and machining response times. For example, assume that the simulation results show that after the correction of this plan, the model dimension error is reduced from the original 0.03 mm to 0.005 mm, the shape deviation is improved by 0.2%, and the response time is controlled within 8 ms. Simulation correction refers to simulating the effect of an arbitrary process plan on the real-time workpiece actual model for machining correction, predicting its compensation ability for machining errors, and recording relevant correction data.

[0076] Read the predetermined correction evaluation indicators, that is, the standards preset to evaluate the quality of correction plans, including correction accuracy (such as the correction errors of dimensions, shapes, positions), correction quality (such as surface roughness, machining defect rate), correction performance (such as correction response speed, real-time performance), and correction stability (such as robustness under different working conditions). Match the simulation correction data with the predetermined indicators and extract the corresponding correction evaluation parameters. Any correction evaluation parameter refers to the specific numerical parameter obtained through matching and extraction, which reflects the effects of a certain candidate correction plan in terms of correction accuracy, quality, performance, and stability. Normalize any correction evaluation parameter to eliminate the dimensional differences of different indicators. For example, the normalized correction accuracy parameter is 0.94, the correction quality parameter is 0.90, the correction performance parameter is 0.92, the correction stability parameter is 0.88, and the correction fitness is 0.91.

[0077] Mutation weighted calculation is based on the normalized parameters. Use a certain weight factor to weight each evaluation parameter and introduce a certain mutation mechanism (such as random perturbation or dynamic adjustment of weights) to enhance the algorithm's ability for diversity and local optimality. Here, mutation can be understood as making appropriate random adjustments to the weights or parameter values to enhance the robustness and global search ability of the optimization. The core idea of mutation weighted calculation is that if the variation range of a certain parameter is large (high degree of dispersion), it means that this parameter has a greater impact on the final result and should be given a higher weight; if the variation range of a certain parameter is small (relatively stable), the weight is relatively small.

[0078] After the preliminary normalization process and mutation weighted calculation, each candidate correction scheme obtains an arbitrary correction fitness value, which comprehensively reflects indicators such as correction accuracy, correction quality, correction performance, and correction stability. The higher the value, the more the scheme meets the processing objectives. Maximizing the fitness value of the arbitrary correction fitness is used as the optimization objective to find a candidate scheme in the correction optimization space such that its arbitrary correction fitness reaches the highest level. At the same time, during the optimization process, using the model comparison deviation as the evaluation objective or constraint condition, the deviation may be reduced, that is, minimizing the difference between the actual processing model and the preset model, thereby ensuring that the processing accuracy meets the design requirements.

[0079] Randomly extract a candidate process plan from the correction optimization space, and each plan obtains its arbitrary correction fitness through the aforementioned steps. The fitness of each candidate plan is obtained from the previous mutation weighted calculation. Using intelligent optimization methods such as genetic algorithms or particle swarm optimization, perform operations such as selection, crossover, and mutation on the candidate plans to generate the next generation of candidate plans. The new generation of candidate plans then undergoes simulation correction and fitness calculation, continuously comparing the fitness of all candidate plans. When the iteration reaches a predetermined number of times (such as 50 times, 100 times) or the fitness improvement meets the set convergence criteria, stop the iteration. In each iteration, the system records the fitness values of each candidate plan and compares the one with the highest fitness among all current plans. When the iteration terminates, the candidate plan with the highest fitness is determined as the optimal correction process plan and is denoted as the optimal correction strategy.

[0080] Constrained by the target process requirements, randomly extract candidate process plans within the correction optimization space, perform correction simulation on the actual real-time workpiece model, record and evaluate the correction data, match and extract the simulation results according to the predetermined correction evaluation indicators (correction accuracy, quality, performance, and stability), obtain the fitness of the candidate plans through normalization and mutation weighted calculation, and through iterative optimization, select the plan with the highest fitness as the optimal correction strategy, significantly improving the processing quality of the mold, reducing the scrap rate, and enhancing production efficiency.

[0081] S700: Dynamically process and correct the target mold according to the optimal correction strategy.

[0082] Specifically, the optimal correction strategy includes specific combinations of process parameters, such as cutting speed, feed rate, tool compensation value, tool path adjustment, etc. Its goal is to make the state of the actual processed mold as close as possible to the design preset requirements. Send the determined optimal correction strategy to the machine tool fieldbus control system to automatically adjust the processing parameters of the machine tool and perform dynamic processing correction on the target mold. For example, adjust the tool path compensation value, cutting speed, and feed rate according to the strategy requirements.

[0083] During the machining process, a sensor network (such as laser rangefinders, displacement sensors, strain gauges, etc.) continuously collects data on the machining state of the mold and feeds it back to the machine tool fieldbus control system. The machine tool fieldbus control system determines whether the machining deviation has been effectively corrected based on the feedback data. If the deviation still exists, parameter fine-tuning is performed again according to the optimal correction strategy to achieve dynamic closed-loop compensation. After dynamic compensation using the optimal correction strategy, the deviation between the actual machined mold and the preset design is significantly reduced. The dynamic correction process realizes millisecond-level real-time feedback and adjustment, avoiding error accumulation and machining defects, and improving production stability.

[0084] In summary, the dynamic correction method for mold machining deviation based on real-time monitoring provided by this application has the following beneficial effects:

[0085] By reading the target machining plan of the target mold, where the target machining plan includes target design parameters and target process requirements; performing collaborative analysis on the target design parameters and the target process requirements to obtain a real-time workpiece preset model; dynamically monitoring the machining process of the target mold through a sensor network to obtain real-time sensing information; analyzing the real-time sensing information to obtain the real-time state parameters of the target mold, and constructing a real-time workpiece actual model based on the real-time state parameters; comparing the real-time workpiece actual model with the real-time workpiece preset model to obtain a model comparison deviation; performing correction optimization with the model comparison deviation as the optimization constraint to obtain an optimal correction strategy; and dynamically machining and correcting the target mold according to the optimal correction strategy. That is, by obtaining the target design parameters and target process requirements through the machining plan, constructing a real-time workpiece preset model, dynamically monitoring the mold machining process and constructing a real-time workpiece actual model, comparing the preset model with the actual model, performing optimization based on the deviation, determining the optimal correction plan to correct the machining process of the target mold, and real-time adjusting the machining parameters through the machine tool fieldbus control system, the accuracy and quality of mold machining are improved, thereby improving production efficiency.

[0086] Embodiment 2, based on the same inventive concept as the dynamic correction method for mold machining deviation based on real-time monitoring in the foregoing Embodiment 1, this application also provides a dynamic correction system for mold machining deviation based on real-time monitoring. Please refer to the appendix Figure 2 The dynamic correction system for mold machining deviation based on real-time monitoring includes:

[0087] A pre - plan reading module 11 for reading a target processing pre - plan of a target mold, where the target processing pre - plan includes target design parameters and target process requirements; a collaborative analysis module 12 for performing collaborative analysis on the target design parameters and the target process requirements to obtain a real - time workpiece preset model; a processing monitoring module 13 for dynamically monitoring the processing process of the target mold through a sensor network to obtain real - time sensing information; a model construction module 14 for analyzing the real - time sensing information to obtain real - time state parameters of the target mold and constructing a real - time workpiece actual model according to the real - time state parameters; a model deviation comparison module 15 for comparing the real - time workpiece actual model with the real - time workpiece preset model to obtain a model comparison deviation; a strategy optimization module 16 for performing correction optimization with the model comparison deviation as an optimization constraint to obtain an optimal correction strategy; a processing correction module 17 for dynamically correcting the processing of the target mold according to the optimal correction strategy.

[0088] Further, the collaborative analysis module 12 in the mold processing deviation dynamic correction system based on real - time monitoring is further configured to: construct an initial geometric model according to the design shape, design interior, and design relative position in the target design parameters; integrate the target process requirements into the initial geometric model to obtain an initial model; obtain the real - time moment, and perform a processing process analysis on the initial model in combination with the real - time moment to obtain the model at the real - time moment, denoted as the real - time workpiece preset model.

[0089] Further, the processing monitoring module 13 in the mold processing deviation dynamic correction system based on real - time monitoring is further configured to: perform dynamic processing monitoring on the target mold through a displacement sensor in the sensor network to obtain real - time displacement; perform dynamic processing monitoring on the target mold through a strain gauge in the sensor network to obtain real - time strain; perform dynamic processing monitoring on the target mold through a laser rangefinder in the sensor network to obtain real - time processing accuracy; and form the real - time sensing information based on the real - time displacement, the strain, and the real - time processing accuracy.

[0090] Further, the model construction module 14 in the mold processing deviation dynamic correction system based on real - time monitoring is further configured to: perform standardization processing on the real - time sensing information to obtain real - time standard sensing information; introduce a predetermined sensing feature index and perform traversal extraction on the real - time standard sensing information to obtain real - time standard feature parameters; and render and fuse the real - time standard feature parameters into the initial model of the target mold to obtain the real - time workpiece actual model.

[0091] Further, the model construction module 14 in the dynamic correction system for mold processing deviation based on real-time monitoring is further configured to: The predetermined sensing feature indicators include displacement sensing feature indicators, strain sensing feature indicators, and machining accuracy sensing feature indicators.

[0092] Further, the model deviation comparison module 15 in the dynamic correction system for mold processing deviation based on real-time monitoring is further configured to: introduce a model size deviation evaluation function to perform size deviation evaluation and analysis on the real-time workpiece actual model and the real-time workpiece preset model to obtain a model size deviation; introduce a model shape deviation evaluation function to perform shape deviation evaluation and analysis on the real-time workpiece actual model and the real-time workpiece preset model to obtain a model shape deviation; introduce a model position deviation evaluation function to perform position deviation evaluation and analysis on the real-time workpiece actual model and the real-time workpiece preset model to obtain a model position deviation; take the mean of the model size deviation, the model shape deviation, and the model position deviation as the model comparison deviation; wherein, the formula of the model size deviation evaluation function is as follows: ; the formula of the model shape deviation evaluation function is as follows: ; the formula of the model position deviation evaluation function is as follows: ; wherein, 、 and respectively represent the model size deviation, the model shape deviation, and the model position deviation, 、 and respectively represent the size, shape, and position of the real-time workpiece actual model at the th model part, 、 and respectively represent the size, shape, and position of the real-time workpiece preset model at the th model part, represents the total number of model parts for comparison.

[0093] Further, the strategy optimization module 16 in the dynamic correction system for mold processing deviation based on real-time monitoring is further configured to: establish a correction optimization space with the target process requirements as constraints, and randomly extract any process plan in the correction optimization space, where the any process plan is different from the real-time process plan of the target mold; perform simulation correction on the real-time workpiece actual model based on the any process plan, and record any correction data; read a predetermined correction evaluation index, and perform matching extraction on the any correction data based on the predetermined correction evaluation index to obtain any correction evaluation parameter; perform mutation weighted calculation on the normalized any correction evaluation parameter to obtain any correction fitness; perform iterative optimization with the maximum fitness value of the any correction fitness as the target to obtain an optimal correction process plan, which is denoted as the optimal correction strategy.

[0094] Further, the strategy optimization module 16 in the dynamic correction system for mold processing deviation based on real-time monitoring is further configured to: the predetermined correction evaluation indexes include correction accuracy, correction quality, correction performance, and correction stability.

[0095] The various embodiments in this specification are described in a progressive manner. The key point of each embodiment is the difference from other embodiments. The foregoing Figure 1 The dynamic correction method and specific examples for mold processing deviation based on real-time monitoring in the first embodiment are equally applicable to the dynamic correction system for mold processing deviation based on real-time monitoring in this embodiment. Through the foregoing detailed description of the dynamic correction method for mold processing deviation based on real-time monitoring, those skilled in the art can clearly know the dynamic correction system for mold processing deviation based on real-time monitoring in this embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0096] Embodiment 3, based on the same inventive concept as the dynamic correction method for mold processing deviation based on real-time monitoring in the foregoing Embodiment 1, the present application further provides an electronic device, including: at least one processor; 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 so that the at least one processor can execute the steps of the dynamic correction method for mold processing deviation based on real-time monitoring according to any one of the foregoing Embodiment 1.

[0097] Appendix Figure 3 is a schematic structural diagram of an exemplary electronic device of the present application. In Figure 3Among them, the bus architecture is represented by bus 300. Bus 300 may include any number of interconnected buses and bridges. Bus 300 connects various circuits including one or more processors represented by processor 302 and a memory represented by memory 304 together. Bus 300 may also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, etc., which are well known in the art, and thus will not be further described herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, i.e., a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 may be used to store data used by processor 302 when performing operations.

[0098] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

[0099] Obviously, for those skilled in the art, without departing from the principles of the present application, several improvements and modifications can also be made to the present application, and these improvements and modifications also fall within the protection scope of the present application.

Claims

1. A dynamic correction method for mold processing deviation based on real-time monitoring, characterized in that: include: Reading a target processing plan of a target mold, wherein the target processing plan includes target design parameters and target process requirements; The target design parameters and the target process requirements are collaboratively analyzed to obtain a real-time workpiece preset model, which includes: Constructing an initial geometric model according to the design shape, design interior and design relative position in the target design parameters; Integrating the target process requirements into the initial geometric model to obtain an initial model; Acquire the real time, and analyze the processing of the initial model in combination with the real time to obtain the model at the real time, which is recorded as the real-time workpiece preset model; Dynamically monitoring the processing process of the target mold through a sensor network to obtain real-time sensor information; Analyzing the real-time sensing information to obtain the real-time state parameters of the target mold, and constructing a real-time workpiece actual model according to the real-time state parameters, including: Performing standardization processing on the real-time sensing information to obtain real-time standard sensing information; Introducing a predetermined sensor characteristic index and traversing and extracting the real-time standard sensor information to obtain a real-time standard characteristic parameter; Rendering and fusing the real-time standard feature parameters to the initial model of the target mold to obtain the real-time workpiece actual model; Comparing the real-time workpiece actual model with the real-time workpiece preset model to obtain a model comparison deviation; The model comparison deviation is used as an optimization constraint to perform correction optimization and obtain the optimal correction strategy, which includes: Establishing a modified optimization space with the target process requirement as a constraint, and randomly extracting any process solution in the modified optimization space, wherein the arbitrary process solution is different from the real-time process solution of the target mold; Performing simulation correction on the real-time workpiece actual model based on the arbitrary process scheme, and recording arbitrary correction data; Reading a predetermined correction evaluation index, and matching and extracting the arbitrary correction data based on the predetermined correction evaluation index to obtain an arbitrary correction evaluation parameter; Performing a variation weighted calculation on the normalized arbitrary modified evaluation parameter to obtain an arbitrary modified fitness; Iterative optimization is performed with the goal of maximizing the fitness value of the arbitrary modified fitness to obtain an optimal modified process solution, which is recorded as the optimal modified strategy; The target mold is dynamically processed and corrected according to the optimal correction strategy.

2. The method for dynamic correction of mold processing deviation based on real-time monitoring according to claim 1 is characterized in that: The processing process of the target mold is dynamically monitored through the sensor network to obtain real-time sensor information, including: Dynamically monitor the processing of the target mold by using a displacement sensor in the sensor network to obtain real-time displacement; Dynamically monitor the processing of the target mold through strain gauges in the sensor network to obtain real-time strain; Dynamically monitor the processing of the target mold through the laser rangefinder in the sensor network to obtain real-time processing accuracy; The real-time sensing information is composed based on the real-time displacement, the real-time strain and the real-time processing accuracy.

3. The method for dynamic correction of mold processing deviation based on real-time monitoring according to claim 1 is characterized in that: The predetermined sensing characteristic indexes include displacement sensing characteristic indexes, strain sensing characteristic indexes and processing accuracy sensing characteristic indexes.

4. The method for dynamic correction of mold processing deviation based on real-time monitoring according to claim 1 is characterized in that: Comparing the real-time workpiece actual model with the real-time workpiece preset model to obtain a model comparison deviation includes: Introducing a model size deviation evaluation function to perform size deviation evaluation analysis on the real-time workpiece actual model and the real-time workpiece preset model to obtain a model size deviation; Introducing a model shape deviation evaluation function to perform shape deviation evaluation analysis on the real-time workpiece actual model and the real-time workpiece preset model to obtain a model shape deviation; Introducing a model position deviation evaluation function to perform position deviation evaluation analysis on the real-time workpiece actual model and the real-time workpiece preset model to obtain a model position deviation; Taking the average of the model size deviation, the model shape deviation and the model position deviation as the model comparison deviation; Among them, the formula of the model size deviation evaluation function is as follows: ； The formula of the model shape deviation evaluation function is as follows: ； The formula of the model position deviation evaluation function is as follows: ； in, , and They represent the model size deviation, model shape deviation and model position deviation respectively. , and Respectively represent the actual model of the real-time workpiece in The size, shape and position of each model part, , and Respectively represent the real-time workpiece preset model in The size, shape and position of each model part, Indicates the total number of model parts compared.

5. The method for dynamic correction of mold processing deviation based on real-time monitoring according to claim 1 is characterized in that: The predetermined correction evaluation indexes include correction accuracy, correction quality, correction performance and correction stability.

6. The dynamic correction system of mold processing deviation based on real-time monitoring is characterized by: The steps for implementing the mold processing deviation dynamic correction method based on real-time monitoring as described in any one of claims 1 to 5, the mold processing deviation dynamic correction system based on real-time monitoring comprises: A plan reading module, used for reading a target processing plan of a target mold, wherein the target processing plan includes target design parameters and target process requirements; A collaborative analysis module, used for collaboratively analyzing the target design parameters and the target process requirements to obtain a real-time workpiece preset model; A processing monitoring module, used to dynamically monitor the processing process of the target mold through a sensor network to obtain real-time sensor information; A model building module, used for analyzing the real-time sensing information to obtain the real-time state parameters of the target mold, and building a real-time workpiece actual model according to the real-time state parameters; A model deviation comparison module, used for comparing the real-time workpiece actual model with the real-time workpiece preset model to obtain a model comparison deviation; A strategy optimization module is used to perform correction optimization using the model comparison deviation as an optimization constraint to obtain an optimal correction strategy; A processing correction module is used to perform dynamic processing correction on the target mold according to the optimal correction strategy.

7. An electronic device, characterized in that: include: at least one processor; a memory communicatively coupled 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 steps of the dynamic correction method of mold processing deviation based on real-time monitoring as described in any one of claims 1 to 5.

Images