Flat grinder adaptive control optimization method for mold part manufacturing

Abstract

The application discloses a planar grinding machine adaptive control optimization method for mold part manufacturing, and belongs to the technical field of intelligent manufacturing, wherein the method comprises the following steps: processing prediction modeling of the manufacturing design information by using digital twin technology; collecting mold part manufacturing data sets of the planar grinding machine, and performing retrieval matching based on the manufacturing design information and the mold part manufacturing data sets; processing production and real-time monitoring of a target mold part based on target grinding machine processing parameters; processing prediction of mold part processing real-time data by using a mold part digital twin model; adaptive optimization of the target grinding machine processing parameters based on mold part prediction manufacturing information, and adaptive optimization control of the target mold part by using the optimized grinding machine processing parameters. The application solves the technical problems in the prior art that mold part processing parameters cannot be dynamically optimized, processing precision and efficiency are difficult to satisfy simultaneously, and thus processing quality is unstable and trial and error cost is high.

Description

Technical Field

[0001] This invention relates to the field of intelligent manufacturing technology, and more specifically to an adaptive control optimization method for surface grinders used in mold component manufacturing. Background Technology

[0002] Mold components have wide and important applications in modern manufacturing, including the automotive, electronics, and home appliance industries, which all place stringent requirements on the high precision and stability of mold components. To meet the functional requirements and appearance quality of products, the mold manufacturing process often involves complex multi-stage machining processes. Surface grinding, as a commonly used process in mold finishing, must ensure high-precision shape and dimensions while also considering multiple indicators such as material properties, surface roughness, and machining efficiency.

[0003] With the continuous advancement of intelligent manufacturing and digital transformation, the industry is increasingly focusing on improving the processing quality and efficiency of mold components through digital twin technology, big data analysis, and advanced predictive algorithms. Existing surface grinder controls mostly rely on fixed empirical parameters or semi-automatic parameter compensation methods, which cannot adaptively adjust based on real-time processing conditions, nor can they promptly predict and correct dynamic changes such as wheel wear, grinding temperature, and part deformation. Therefore, there is an urgent need for an optimization method that integrates digital twin technology and intelligent algorithms to dynamically monitor and adjust processing parameters, comprehensively improving the efficiency and quality of mold component manufacturing. Summary of the Invention

[0004] This application provides an adaptive control optimization method for surface grinders used in mold component manufacturing, aiming to solve the technical problems in the prior art where the processing parameters of mold components cannot be dynamically optimized, and the processing accuracy and efficiency are difficult to meet simultaneously, resulting in unstable processing quality and high trial and error costs.

[0005] In view of the above problems, this application provides an adaptive control optimization method for surface grinders used in mold component manufacturing.

[0006] This application provides an adaptive control optimization method for a surface grinder used in mold component manufacturing. The method includes: acquiring manufacturing design information of a target mold component; using digital twin technology to perform processing prediction modeling on the manufacturing design information to generate a digital twin model of the mold component; collecting a mold component manufacturing dataset for the surface grinder; performing a search and matching based on the manufacturing design information and the mold component manufacturing dataset to determine the target grinder processing parameters; processing and real-time monitoring of the target mold component based on the target grinder processing parameters to obtain real-time processing data of the mold component; using the digital twin model of the mold component to perform processing prediction on the real-time processing data of the mold component to obtain predicted manufacturing information of the mold component; adaptively optimizing the target grinder processing parameters based on the predicted manufacturing information of the mold component, outputting optimized grinder processing parameters, and adaptively optimizing the control of the target mold component using the optimized grinder processing parameters.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: By adopting a technical solution that involves acquiring mold manufacturing design information and generating a digital twin model of the mold using digital twin technology, collecting surface grinder manufacturing data and performing matching optimization, and monitoring processing data in real time and performing adaptive parameter optimization based on prediction results, this solution solves the technical problems in existing technologies where mold component processing parameters cannot be dynamically optimized, processing accuracy and efficiency are difficult to meet simultaneously, resulting in unstable processing quality and high trial-and-error costs. It achieves the technical effects of real-time prediction of processing results, dynamic adjustment of processing parameters, and improvement of processing accuracy and efficiency, providing an efficient and intelligent optimization method for the manufacturing of complex mold components.

[0008] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0009] Figure 1 A flowchart illustrating an adaptive control optimization method for surface grinders used in mold component manufacturing is provided for embodiments of this application.

[0010] Figure 2 This application provides a flowchart illustrating the determination of target grinding parameters in an adaptive control optimization method for surface grinders used in mold component manufacturing. Detailed Implementation

[0011] The overall concept of the technical solution provided in this application is as follows: This application provides an adaptive control optimization method for surface grinders used in mold component manufacturing. First, mold manufacturing design information is acquired and a digital twin model is established. Then, surface grinder machining data is collected, matched, and optimized to determine initial machining parameters. During machining, data is monitored in real time, and predictions are made using the digital twin model. Based on the prediction results, machining parameters are adjusted to achieve adaptive optimization control.

[0012] After introducing the basic principles of this application, various non-limiting embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0013] Example 1, as Figure 1 As shown in the embodiments of this application, an adaptive control optimization method for a surface grinder used in mold component manufacturing is provided. The method includes: Step S100: Obtain the manufacturing design information of the target mold component, and use digital twin technology to perform processing prediction modeling on the manufacturing design information to generate a digital twin model of the mold component.

[0014] Specifically, manufacturing design information refers to various data used to describe the design requirements of mold components, including but not limited to geometric structure, dimensional tolerances, material properties, heat treatment requirements, and functional requirements. A digital twin model of a mold component refers to a virtual model constructed using digital twin technology. It not only includes the three-dimensional geometric shape of the mold component but also integrates multi-dimensional information such as its material properties, dynamic data of the processing process, and timing predictions, enabling prediction and feedback of the actual processing process.

[0015] First, 3D structural design drawings of the mold components need to be obtained from CAD software, and relevant manufacturing design information such as part processing requirements, material grades, and heat treatment data need to be retrieved from the enterprise's PLM (Product Lifecycle Management) system or MES (Manufacturing Execution System). Next, based on this design information, the 3D geometry and material properties of the parts are integrated in a 3D modeling tool to construct a preliminary virtual model. Then, digital twin technology is introduced to establish a processing prediction model by matching the virtual model with historical processing parameters collected by sensors. Finite element analysis software can be used to numerically simulate stress and deformation during the grinding process, or deep learning algorithms in Python or MATLAB can be used to train time-series predictions on historical processing data, thereby achieving the fusion between the virtual model and dynamic processing characteristics. Once the digital twin model is established, it can determine the effectiveness of the current processing strategy based on real-time or predicted processing status, laying the foundation for adaptive optimization of subsequent process parameters.

[0016] This step significantly shortens the machining parameter debugging cycle and greatly improves the predictability of machining by constructing a digital twin model of the mold component.

[0017] Step S200: Collect and obtain the mold component manufacturing dataset of the surface grinder, and perform a search and matching based on the manufacturing design information and the mold component manufacturing dataset to determine the target grinder processing parameters.

[0018] Specifically, the mold component manufacturing dataset refers to the collection of historical data recorded and stored during the processing of mold components, including processing parameters (such as depth of cut, grinding wheel speed, and feed rate), processing conditions (such as vibration amplitude and temperature), processing results (such as surface roughness and dimensional tolerances), and related equipment operating data. The target grinding machine processing parameters refer to the recommended surface grinder operating parameters for actual processing after retrieval, matching, and optimization, such as grinding wheel speed, feed rate, and depth of cut, which can meet the mold design requirements.

[0019] First, a dataset of mold component manufacturing data is collected from a production database or sensor system. This data includes parameters and results recorded during historical processing and is stored in a relational database (such as MySQL) or a big data platform (such as Hadoop). Next, the acquired manufacturing design information is used as input, including the mold's geometry, material properties, and target surface quality requirements. Then, based on the manufacturing design information and historical data, a retrieval and matching algorithm is used for analysis. The algorithm searches the historical data for the processing cases most similar to the current requirements based on the design information and outputs preliminary matching processing parameters. After matching, the preliminary matching parameters are optimized based on specific mold processing requirements.

[0020] This step enables precise matching and optimization of processing parameters from historical data to actual requirements, significantly reducing trial-and-error time during parameter setting and improving processing efficiency. Simultaneously, by combining retrieval and matching methods with optimization algorithms, optimal parameter combinations can be recommended for different design needs, ensuring that processing quality and accuracy meet design requirements.

[0021] Step S300: Based on the target grinding machine processing parameters, process and monitor the target mold component in real time to obtain real-time processing data of the mold component.

[0022] Specifically, the optimized target grinding parameters are input into the surface grinder control system, for example, setting the grinding wheel speed to 3000 RPM, the depth of cut to 0.5 mm, and the feed rate to 800 mm / min. Then, the grinder is started to process the target mold part.

[0023] During the machining process, real-time data is collected through a real-time monitoring system. For example, vibration sensors (such as accelerometers) mounted on the grinding machine can collect vibration signals and measure the contact state between the grinding wheel and the workpiece during machining; infrared temperature sensors can monitor temperature changes on the machined surface; laser measuring instruments or 3D scanners can capture the dimensions and surface roughness of mold parts. The data is then transmitted in real time to a central processing unit for analysis via an industrial data acquisition system (such as a PLC or SCADA).

[0024] By implementing processing and real-time monitoring based on target processing parameters, dynamic changes during the processing can be effectively captured, ensuring processing accuracy and stability. The real-time monitoring system can promptly identify potential problems and respond quickly, preventing the further spread of processing defects.

[0025] Step S400: Use the digital twin model of the mold component to predict the processing of the real-time data of the mold component to obtain the predicted manufacturing information of the mold component.

[0026] Specifically, mold component predictive manufacturing information refers to the processing result data predicted through digital twin models, including information such as the quality, shape characteristics, and error distribution of the processed surface, providing a basis for real-time optimization of the processing process.

[0027] First, a sensor system is used to collect real-time data on the machining of mold components. For example, an accelerometer acquires vibration data, an infrared sensor records surface temperature changes, and a laser scanner captures the geometric information of the machined surface in real time. This data is then transmitted to the central control system via an industrial data acquisition system (such as a PLC or IoT gateway).

[0028] Subsequently, the collected real-time data is input into the digital twin model of the mold component. The digital twin model, through an algorithm that integrates a 3D solid model, a machining state prediction network, and historical data, simulates and predicts the current machining state. For example, the model can predict surface roughness or thermal deformation risks using real-time temperature and depth-of-cut data.

[0029] The model's prediction process can be implemented using deep learning frameworks. For example, a machining prediction network trained on historical data can output the machining result (such as surface quality or dimensional deviation) at the next moment after inputting real-time machining parameters.

[0030] By using digital twin models to predict real-time processing data, potential problems in the process can be identified in advance, preventing defects from escalating and improving processing quality and efficiency. Furthermore, the prediction results can provide data support for real-time parameter optimization, further reducing scrap rates and processing time.

[0031] Step S500: Based on the predicted manufacturing information of the mold component, adaptively optimize the processing parameters of the target grinding machine, output the optimized processing parameters of the grinding machine, and adaptively optimize and control the target mold component through the optimized processing parameters of the grinding machine.

[0032] Specifically, the optimized machining parameters for the grinding machine are the final machining parameters output after adaptive optimization, which can solve deviation problems and ensure machining quality. The optimized parameters are then applied to the actual machining process, forming a closed-loop control. Adaptive optimization control is a control method that dynamically adjusts the machining process based on real-time feedback data and optimization results, automatically adjusting machining parameters to ensure the entire machining process is stable and efficient.

[0033] First, predictive manufacturing information for the mold components is obtained from the digital twin model, including predicted surface quality values, dimensional deviations, and machining efficiency indicators. Next, the predicted information is compared with manufacturing design requirements, the deviation is calculated, and this information is input into an optimization algorithm. For example, if the predicted surface roughness value is too high, it can be improved by adjusting the grinding wheel speed or reducing the depth of cut. This optimization process can employ particle swarm optimization (PSO), genetic algorithms (GA), or gradient descent methods. Parameter optimization is implemented using Python's SciPy library, with the optimization objective set as minimizing the surface roughness deviation while constraining the machining efficiency to be no less than a set value.

[0034] After optimization, the adjusted grinding machine parameters are output, such as changing the grinding wheel speed from 3000 RPM to 3200 RPM and reducing the depth of cut from 0.5 mm to 0.4 mm. The optimized parameters are then reapplied to the grinding machine, and the target mold part continues to be machined. During the machining process, new machining data is acquired through a real-time monitoring system, and predictions and optimizations are performed again, forming a closed-loop adaptive control.

[0035] Through adaptive optimization based on predictive information, processing parameters can be dynamically adjusted to ensure that the processing results meet design requirements and significantly improve processing quality and efficiency. Closed-loop control of the processing process is achieved, reducing trial-and-error costs and manual intervention.

[0036] Furthermore, the generation of the digital twin model of the mold component includes: obtaining the structural design information and processing requirement attribute information of the mold component based on the manufacturing design information; performing three-dimensional modeling and attribute assignment based on the structural design information and processing requirement attribute information of the mold component to generate a three-dimensional solid model of the mold component; collecting and acquiring the historical processing dataset of the mold component, using a recurrent neural network structure to train the historical processing dataset of the mold component for processing prediction, and obtaining a processing status prediction network for the mold component; and using digital twin technology to perform twin fusion modeling of the three-dimensional solid model of the mold component and the processing status prediction network of the mold component to generate the digital twin model of the mold component.

[0037] Specifically, mold component structural design information refers to the geometric data of mold components, such as shape, size, and positional relationships. This is typically generated using computer-aided design (CAD) software and directly reflects the physical shape and spatial layout of the mold. Mold component processing requirement attribute information refers to the technical requirements that must be met during mold manufacturing, including material properties (such as hardness and thermal conductivity), surface roughness, tolerance range, and processing efficiency. A 3D solid model is a 3D visualization model of the mold component, containing geometric and attribute information. A historical processing dataset for mold components is a collection of data recorded during past processing of mold components, including processing parameters and environmental conditions. This data can be used as training data for machine learning models. The processing state prediction network is a predictive model trained based on machine learning algorithms, used to predict the state or outcome during processing based on input processing parameters, such as vibration amplitude, temperature changes, or surface roughness.

[0038] First, structural design information and processing requirement attributes are extracted from the manufacturing design information of the target mold component. AutoCAD software can be used to extract the mold's 3D geometric information. Next, 3D modeling tools are used to create a 3D model based on the extracted information. The 3D solid model needs to include not only the mold's geometric features but also material properties and tolerance information.

[0039] After acquiring the 3D solid model, historical machining datasets of the mold components are collected, such as historical data recorded using industrial sensors or production databases, including feed rate, depth of cut, and post-machining surface roughness. A recurrent neural network is then used to train on this historical data, constructing a machining state prediction network using machine learning frameworks such as Keras or PyTorch.

[0040] Finally, digital twin technology is used to fuse the 3D solid model with a machining state prediction network. In this process, platforms such as Siemens MindSphere or Ansys Twin Builder can be used to bind the mold geometry and machining behavior into the same twin model.

[0041] By generating digital twin models of mold components, potential machining problems, such as excessive vibration or substandard surface roughness, can be predicted before processing. Simulation can then be used to optimize machining parameters, reducing the number of trial and error attempts. During machining, the twin model can monitor the machining status in real time, compare it with the actual machining results, and dynamically adjust machining parameters to ensure that accuracy and quality meet design requirements. Post-machining analysis and feedback can also be used to improve the efficiency of subsequent machining operations. This improves the manufacturing efficiency and precision of mold components.

[0042] Furthermore, obtaining the mold component processing status prediction network includes: cleaning and normalizing the historical processing dataset of the mold components to obtain a standard historical processing dataset of mold components; arranging and integrating the standard historical processing dataset of mold components according to time sequence information and identifying processing status to obtain a time sequence processing sample set of mold components; using a recurrent neural network structure to train processing prediction and calculate loss evaluation on the time sequence processing sample set of mold components to obtain an initial processing status prediction network and prediction network loss data; and using a backpropagation algorithm based on the prediction network loss data to optimize and update the model parameters of the initial processing status prediction network to obtain the mold component processing status prediction network.

[0043] Specifically, time-series information refers to the chronological arrangement of processing data, reflecting the dynamic changes during the processing. Processing status identifiers are labels or classifications for specific states during processing, such as "surface roughness acceptable" or "excessive cutting vibration." These identifiers can be used to guide models in learning the relationship between processing status and parameters. Backpropagation is an optimization algorithm in machine learning used to adjust model parameters. It calculates the error (loss) between the predicted results and the true values ​​and backpropagates the gradient to update the model parameters, gradually optimizing its performance.

[0044] First, a historical processing dataset of mold components is collected, including processing parameters, processing status, and processing results. This data contains noise or outliers, requiring data cleaning, such as deleting abnormal data during equipment malfunctions. Next, the data for each dimension is normalized, converting the values ​​to a uniform range (e.g., 0 to 1) so that the model can process them more efficiently.

[0045] Then, the standardized data is arranged and integrated in chronological order to form a time-series processing sample set; simultaneously, corresponding status labels (such as "qualified" or "unqualified") are assigned based on the processing results. Next, a recurrent neural network (RNN) is used to train the processing sample set. An RNN model is constructed using deep learning frameworks such as PyTorch or TensorFlow, with the time-series processing samples as input and the predicted processing status as output. During training, the error between the model's predicted values ​​and the actual values ​​is calculated, using mean squared error (MSE) as the loss function.

[0046] Finally, the model parameters are optimized using the backpropagation algorithm, and the loss value is gradually reduced through gradient descent, thereby improving the accuracy of model predictions. After training, the final mold component processing state prediction network is obtained. This network can predict the processing state based on the input processing parameters and provide optimization suggestions.

[0047] This step generates a processing status prediction network that significantly improves the controllability and quality prediction capabilities of the processing. The network can predict abnormal states that occur during processing in real time and provide a basis for parameter adjustment, thereby reducing the processing defect rate.

[0048] Furthermore, such as Figure 2 As shown, determining the target grinding machine processing parameters includes: using a classification algorithm to perform retrieval analysis and matching based on the manufacturing design information and the mold component manufacturing dataset to obtain matching grinding machine processing parameters; determining matching parameter manufacturing information based on the matching grinding machine processing parameters; using the difference between the matching parameter manufacturing information and the manufacturing design information as a manufacturing design deviation parameter; and optimizing the matching grinding machine processing parameters based on the manufacturing design deviation parameter to determine the target grinding machine processing parameters.

[0049] Specifically, a classification algorithm is a machine learning algorithm designed to categorize input data into predefined classes based on its features. Here, the classification algorithm analyzes the degree of matching between manufacturing design information and the mold component manufacturing dataset, recommending appropriate machining parameters. Matching parameter manufacturing information refers to machining characteristic information associated with the matching grinding machine machining parameters, such as material properties, surface roughness, and tolerance ranges from historical machining. It is used to assess the gap between the current design requirements and the matching parameters. Manufacturing design deviation parameters are a set of parameters obtained by comparing the differences between the current manufacturing design information and the matching parameter manufacturing information, representing the deviations between the two in terms of dimensions, accuracy, materials, etc. Target grinding machine machining parameters are the final machining parameters, optimized and adjusted to meet the current design requirements, used to guide actual grinding machine machining.

[0050] First, a manufacturing dataset of the target mold component, containing manufacturing design information and historical processing records, is obtained. Then, a classification algorithm (such as KNN or Random Forest) is used to analyze the manufacturing design information, retrieving similar historical processing cases from the mold component manufacturing dataset to recommend preliminary matching grinding machine processing parameters. Next, manufacturing information associated with the matching processing parameters is extracted, such as surface roughness and dimensional deviations achieved in historical processing. This matching parameter manufacturing information is compared with the current manufacturing design information, and the differences are calculated to generate manufacturing design deviation parameters. Finally, the matching grinding machine processing parameters are optimized based on the manufacturing design deviation parameters. An optimization algorithm (such as particle swarm optimization or genetic algorithm) is used to adjust the preliminary matching parameters to better meet the current design requirements. After optimization, the determined parameters are the target grinding machine processing parameters.

[0051] By employing classification algorithms for retrieval and matching, and combining manufacturing design deviation parameters to optimize and adjust processing parameters, target processing parameters can be recommended quickly and accurately, reducing parameter debugging time and improving processing efficiency and quality.

[0052] Furthermore, determining the target grinding machine processing parameters includes: extracting elements from the manufacturing design information to obtain a set of key manufacturing design elements; using the grinding machine processing parameters as independent variables and each key element in the set of key manufacturing design elements as dependent variables; performing multidimensional fitting on the independent and dependent variables based on the mold component manufacturing dataset to generate a processing parameter-manufacturing design correlation model; and using the processing parameter-manufacturing design correlation model to optimize the matching grinding machine processing parameters based on the manufacturing design deviation parameters to determine the target grinding machine processing parameters.

[0053] Specifically, the key elements set of manufacturing design refers to the core parameters extracted from manufacturing design information that play a decisive role in the machining process. Grinding machine parameters are adjustable variables in the actual machining process, including grinding wheel speed, feed rate, and depth of cut. These parameters directly affect machining accuracy, surface quality, and efficiency. Independent variables are controllable input parameters (such as machining parameters), and dependent variables are output results affected by the input parameters (such as surface roughness or machining time). In this step, the independent variables are the grinding machine parameters, and the dependent variables are each element in the key elements set of manufacturing design. Multidimensional fitting is a mathematical modeling method used to represent the complex nonlinear relationship between independent and dependent variables. Through fitting, a correlation model is generated to predict the impact of different combinations of machining parameters on key elements of manufacturing design. The machining parameter-manufacturing design correlation model is a mathematical model built based on historical data and fitting analysis, describing the relationship between machining parameters and manufacturing design requirements. For example, it can predict the impact of different grinding wheel speeds on surface roughness. Manufacturing design deviation parameters refer to the difference between the current matching parameters and the manufacturing design requirements, and are an important basis for optimizing machining parameters.

[0054] First, key elements are extracted from manufacturing design information to construct a set of key manufacturing design elements. Next, the machining parameters of the grinding machine are defined as independent variables, and the key manufacturing design elements are used as dependent variables. By analyzing historical machining datasets, regression analysis or machine learning methods are used for multidimensional fitting to generate a machining parameter-manufacturing design correlation model. In the generated correlation model, the current manufacturing design deviation parameters are input, and the dependent variable is optimized by adjusting the independent variables to determine the target machining parameters that meet the design requirements.

[0055] By extracting key elements of manufacturing design and establishing a correlation model between processing parameters and manufacturing design, an efficient mapping relationship between processing parameters and design requirements was achieved. Based on the optimization and adjustment of deviation parameters, the optimal target processing parameters can be quickly recommended, significantly improving processing efficiency and quality. Simultaneously, multidimensional fitting using historical data not only improves the accuracy of parameter matching but also gives the correlation model strong generalization ability, adapting to different mold design requirements.

[0056] Furthermore, the output of the optimized grinding machine processing parameters includes: taking the deviation between the predicted manufacturing information of the mold component and the manufacturing design information as the manufacturing processing information to be optimized; performing optimization strategy analysis on the target grinding machine processing parameters based on the manufacturing processing information to be optimized to obtain a processing parameter optimization strategy; and using the processing parameter optimization strategy to adaptively optimize the target grinding machine processing parameters to output the optimized grinding machine processing parameters.

[0057] Specifically, the deviation value of manufacturing design information refers to the difference between predicted manufacturing information and manufacturing design information, such as a predicted surface roughness value higher than the design requirement or dimensional deviations exceeding tolerance ranges. The deviation value indicates a deficiency between machining parameters and design requirements. The manufacturing machining information to be optimized is a dataset integrating the deviation values ​​of predicted manufacturing information and manufacturing design information for mold components, serving as input for further optimization of machining parameters. The machining parameter optimization strategy is a specific operational plan generated based on optimization analysis, used to guide the adjustment of target machining parameters. The optimized machining parameters for the grinding machine are the final set of machining parameters obtained after applying the optimization strategy, used to guide the actual machining process and ensure machining quality and efficiency.

[0058] First, the deviation values ​​between the predicted manufacturing information and the manufacturing design information of the mold components are obtained. Then, these deviation values ​​are input into the optimization strategy analysis module as manufacturing process information to be optimized. Key deviation items and their correlation with processing parameters are identified through data analysis methods (such as principal component analysis and sensitivity analysis). For example, surface roughness deviation is mainly affected by the grinding wheel speed and depth of cut, while dimensional deviation is related to the feed rate.

[0059] Based on this, an optimization strategy for machining parameters is generated using an optimization algorithm. The optimization objective is set to minimize the deviation value, while constraining other indicators (such as machining efficiency and machining time) to remain within a reasonable range. For example, increasing the grinding wheel speed by 10% reduces surface roughness deviation; reducing the depth of cut by 0.1 mm corrects dimensional deviations. The generated optimization strategy is applied to adjust the target machining parameters, outputting the final optimized machining parameters for the grinding machine.

[0060] This step, utilizing predicted manufacturing information and design deviations for optimization, significantly improves the adaptability of processing parameters and the accuracy of processing results. The optimized processing parameters not only meet design requirements but also find the optimal balance between efficiency and quality.

[0061] Furthermore, the output grinding machine optimized processing parameters include: adaptively optimizing the target grinding machine processing parameters using the processing parameter optimization strategy to obtain a processing parameter optimization threshold; randomly selecting multiple processing optimization parameters within the processing parameter optimization threshold, and using the digital twin model of the mold component to perform global optimization on the multiple processing optimization parameters to obtain the grinding machine optimized processing parameters.

[0062] Specifically, the processing parameter optimization threshold refers to the effective range set for the processing parameters after adaptive optimization, used to constrain the adjustment range of the parameters. Randomly selecting multiple processing optimization parameters means randomly generating several sets of processing parameter combinations within the optimization threshold range as candidate parameters for further optimization.

[0063] First, the machining parameters of the target grinding machine are adaptively optimized based on the machining parameter optimization strategy, and an optimization threshold is set for each parameter. For example, by analyzing the prediction results and deviations, the threshold for the grinding wheel speed is set to 3100-3300 RPM, the depth of cut is set to 0.4-0.6 mm, and the feed rate is set to 700-800 mm / min.

[0064] Next, several sets of machining parameter combinations are randomly generated within the optimization threshold range. These candidate parameters can be generated using the Monte Carlo method or Latin hypercube sampling. For example, five sets of parameter combinations are randomly generated within the above range, such as: Set 1: grinding wheel speed 3150 RPM, depth of cut 0.45 mm, feed rate 750 mm / min; Set 2: grinding wheel speed 3200 RPM, depth of cut 0.5 mm, feed rate 780 mm / min; Set 3: grinding wheel speed 3250 RPM, depth of cut 0.4 mm, feed rate 700 mm / min.

[0065] Subsequently, a digital twin model of the mold component is used to simulate and predict the processing results (such as surface roughness, processing time, and dimensional deviation) for each set of candidate parameters, evaluating their processing outcomes. The performance indicators of each set of parameters are obtained through simulation calculations and used as input for subsequent global optimization. A global optimization algorithm (such as genetic algorithm or particle swarm optimization) is applied to find the optimal solution among the candidate parameters. For example, surface roughness, processing time, and dimensional deviation are used as weighted combinations in the objective function, and the set of parameters with the best performance indicators is selected after optimization. Finally, the globally optimized grinding machine processing parameters are output to guide actual processing operations.

[0066] By randomly selecting parameters within the optimization threshold range and using a digital twin model for global optimization, this method ensures that the selection of machining parameters is more scientific and reasonable, avoiding local optima problems. The final output of optimized grinding machine parameters can simultaneously meet multiple requirements such as surface quality, dimensional accuracy, and machining efficiency, improving the stability and consistency of machining results.

[0067] Furthermore, obtaining the optimized machining parameters for the grinding machine includes: using the digital twin model of the mold component to predict the machining of the multiple machining optimization parameters to obtain multiple parameter prediction manufacturing information; performing cross-mutation expansion on the multiple machining optimization parameters based on the multiple parameter prediction manufacturing information to obtain a machining parameter update population; and performing global parameter optimization within the machining parameter update population to obtain the optimized machining parameters for the grinding machine.

[0068] Specifically, parameter prediction manufacturing information is the processing result data obtained by simulating and predicting the combination of processing optimization parameters through a digital twin model of the mold component, such as surface roughness, dimensional accuracy, and processing time. Crossover mutation expansion is an operation in optimization algorithms that aims to generate new candidate parameters (called a "population") through the crossover and random mutation of parameter combinations, thereby expanding the search space and improving optimization performance. The processing parameter update population is a new set of processing parameters generated by the crossover mutation operation, where each set of parameters is an optimization candidate.

[0069] First, a digital twin model of the mold component is used to simulate and predict multiple initially generated combinations of machining optimization parameters, obtaining corresponding parameter prediction manufacturing information. Then, based on the prediction information, a new machining parameter update population is generated through crossover and mutation. For example: Crossover operation: Two sets of parameter combinations (A: grinding wheel speed 3200 RPM, depth of cut 0.5 mm; B: grinding wheel speed 3100 RPM, depth of cut 0.6 mm) are partially swapped to generate a new parameter combination (C: grinding wheel speed 3200 RPM, depth of cut 0.6 mm). Mutation operation: Small perturbations are introduced into randomly selected parameters, such as changing the depth of cut from 0.5 mm to 0.55 mm, or the feed rate from 750 mm / min to 760 mm / min. The generated new population is then simulated and predicted again to evaluate its manufacturing information (such as surface roughness, machining time, and dimensional accuracy), and global optimization is performed on the entire updated population using optimization algorithms (such as genetic algorithms or particle swarm optimization). The optimization objective can be to minimize surface roughness, maximize machining efficiency, or a weighted combination of both. Finally, the optimized grinding parameters after global optimization are output.

[0070] By using a digital twin model of the mold components to simulate and predict candidate parameters, and combining this with crossover mutation to generate a new population, global optimization ensures the comprehensiveness and optimality of the selection of processing parameters.

[0071] In summary, the adaptive control optimization method for surface grinders used in mold component manufacturing provided in this application has the following technical effects: 1. By constructing an adaptive control optimization method for surface grinders, a closed-loop optimization process from mold design information to machining parameters was achieved. Combining digital twin technology, real-time monitoring, and machining parameter optimization, machining strategies can be dynamically adjusted to ensure that the machining results meet design requirements. This method significantly improves the accuracy, efficiency, and stability of mold machining, reduces trial and error and resource waste, and provides a scientific basis for intelligent mold manufacturing.

[0072] 2. By extracting key elements of manufacturing design and constructing a correlation model between processing parameters and manufacturing design, a precise match between processing parameters and design requirements was achieved. Multidimensional fitting modeling effectively uncovered the complex influence of processing parameters on design objectives, providing a scientific basis for parameter optimization. This technology enhances the scientific rigor and adaptability of processing schemes, significantly improving the precision and quality of complex mold manufacturing.

[0073] 3. A digital twin model is used to simulate and predict candidate parameters, and the population is expanded through crossover and mutation. Finally, the optimal combination of processing parameters is obtained through global optimization. This technology significantly improves the efficiency and accuracy of processing parameter optimization, ensuring that the processing results meet design requirements. The global optimization method further reduces trial-and-error costs and significantly improves the level of intelligence in mold manufacturing.

[0074] In summary, any step of the method described above can be stored as a computer instruction or program in an unrestricted computer memory, and can be called and identified by an unrestricted computer processor to implement any method in the embodiments of this application, without any additional restrictions.

[0075] Furthermore, the "first" or "second" mentioned above not only represents a sequential relationship but also a specific concept and / or refers to the possibility of selecting individual or all of multiple elements. Clearly, those skilled in the art can make various modifications and variations to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. An adaptive control optimization method for surface grinders used in mold component manufacturing, characterized in that, The method includes: Obtain the manufacturing design information of the target mold component, and use digital twin technology to perform processing prediction modeling on the manufacturing design information to generate a digital twin model of the mold component; Collect and acquire a mold component manufacturing dataset for a surface grinder, and perform a search and matching based on the manufacturing design information and the mold component manufacturing dataset to determine the target grinder processing parameters; Based on the target grinding machine processing parameters, the target mold component is processed and produced in real time, and real-time monitoring is performed to obtain real-time processing data of the mold component. The digital twin model of the mold component is used to predict the processing of the mold component based on real-time processing data, thereby obtaining predictive manufacturing information for the mold component. Based on the predicted manufacturing information of the mold components, the target grinding machine processing parameters are adaptively optimized, the optimized grinding machine processing parameters are output, and the target mold components are adaptively optimized and controlled using the optimized grinding machine processing parameters. The determination of the target grinding machine processing parameters includes: A classification algorithm is used to retrieve, analyze, and match the manufacturing design information with the mold component manufacturing dataset to obtain matching grinding machine processing parameters. Based on the matching grinding machine processing parameters, determine the manufacturing information of the matching parameters; The difference between the matching parameter manufacturing information and the manufacturing design information is used as the manufacturing design deviation parameter; Based on the manufacturing design deviation parameters, the processing parameters of the matching grinding machine are optimized to determine the processing parameters of the target grinding machine; The generated digital twin model of the mold component includes: Based on the manufacturing design information, obtain mold component structural design information and mold component processing requirement attribute information; Based on the structural design information and processing requirement information of the mold components, a three-dimensional model is created and attributes are assigned to generate a three-dimensional solid model of the mold components. Collect historical processing datasets of mold parts, and use a recurrent neural network structure to train the historical processing datasets of mold parts for processing prediction to obtain a mold part processing status prediction network. The three-dimensional solid model of the mold component and the processing status prediction network of the mold component are fused together using digital twin technology to generate a digital twin model of the mold component. The output grinding machine optimized processing parameters include: The deviation between the predicted manufacturing information and the manufacturing design information of the mold component is used as the manufacturing process information to be optimized. Based on the manufacturing and processing information to be optimized, the target grinding machine processing parameters are analyzed to obtain the processing parameter optimization strategy. The aforementioned machining parameter optimization strategy is used to adaptively optimize the machining parameters of the target grinding machine, and the optimized machining parameters of the grinding machine are output.

2. The adaptive control optimization method for surface grinders used in mold component manufacturing as described in claim 1, characterized in that, The network for predicting the processing status of mold components includes: The historical processing dataset of mold parts is cleaned and normalized to obtain a standard historical processing dataset of mold parts. The historical processing dataset of the standard mold parts is arranged, integrated, and labeled with processing status according to time sequence information to obtain a time sequence processing sample set of mold parts. A recurrent neural network structure is used to train the processing prediction and loss assessment of the time-series processing sample set of the mold parts, so as to obtain the initial processing state prediction network and the prediction network loss data. The model parameters of the initial processing state prediction network are optimized and updated using the backpropagation algorithm based on the loss data of the prediction network, thereby obtaining the mold component processing state prediction network.

3. The adaptive control optimization method for surface grinders used in mold component manufacturing as described in claim 1, characterized in that, The determination of the target grinding machine processing parameters includes: The manufacturing design information is subjected to element extraction to obtain a set of key manufacturing design elements; The grinding machine processing parameters are used as independent variables, and the key elements in the set of key elements of manufacturing design are used as dependent variables. Based on the mold component manufacturing dataset, the independent and dependent variables are fitted in multiple dimensions to generate a processing parameter-manufacturing design correlation model. The machining parameters of the matching grinding machine are optimized based on the manufacturing design deviation parameters using the machining parameter-manufacturing design correlation model to determine the target grinding machine machining parameters.

4. The adaptive control optimization method for surface grinders used in mold component manufacturing as described in claim 1, characterized in that, The output grinding machine optimized processing parameters include: The machining parameter optimization strategy is used to adaptively optimize the machining parameters of the target grinding machine to obtain the machining parameter optimization threshold; Multiple processing optimization parameters are randomly selected within the processing parameter optimization threshold, and the digital twin model of the mold component is used to perform global optimization on the multiple processing optimization parameters to obtain the grinding machine optimized processing parameters.

5. The adaptive control optimization method for surface grinders used in mold component manufacturing as described in claim 4, characterized in that, The process of obtaining optimized grinding parameters includes: The digital twin model of the mold component is used to predict the processing of the multiple processing optimization parameters, thereby obtaining manufacturing information for multiple parameters. Based on the manufacturing information predicted by the multiple parameters, the multiple processing optimization parameters are cross-mutated and expanded to obtain a processing parameter update population. Global parameter optimization is performed within the processing parameter update population to obtain the optimized processing parameters for the grinding machine.

Images