Machining parameter self-adaptive optimization method and device based on workpiece recognition

Abstract

The invention relates to the field of machining parameter optimization, in particular to a machining parameter self-adaptive optimization method and device based on workpiece recognition, and the method comprises the steps: obtaining the multi-source feature information of a to-be-machined workpiece when a machining instruction is received; matching a preset process knowledge base according to the multi-source feature information, and generating initial processing parameters and process target data; dynamic state data in the machining process are obtained in real time, wherein the dynamic state data comprise change parameters of the workpiece and feedback parameters of machining equipment; based on the dynamic state data, whether deviation exists between the dynamic state data and the process target data is analyzed; and if deviation exists between the dynamic state data and the preset process target, adjusting parameters are generated according to the dynamic state data. By obtaining workpiece change parameters and equipment feedback parameters in real time, the machining state can be dynamically monitored, and deviation can be found and recognized in time. Through comparison with preset process target data, existence of deviation can be accurately identified, and then necessary adjustment measures are taken.

Description

Technical Field

[0001] This application relates to the technical field of machining parameter optimization, and particularly to a method and device for adaptively optimizing machining parameters based on workpiece recognition. Background Art

[0002] The optimization of machining parameters for machining equipment refers to the process of adjusting and optimizing machining parameters through scientific methods according to various factors such as the different characteristics of workpieces, the performance of machining equipment, and the machining environment during the manufacturing process, so as to achieve the best machining effect. This process involves multiple aspects, aiming to improve machining accuracy, reduce machining time, lower energy consumption, extend equipment life, and ultimately enhance production efficiency and product quality.

[0003] Traditional numerical control machining systems usually assume that the materials being machined (such as aluminum alloys, steel, etc.) have fixed and consistent physical properties, such as hardness, ductility, etc. These physical properties are generally processed through preset standard material data. However, these preset data are not always accurate. Especially in mass production, due to batch differences in raw materials, there may be significant differences in the physical properties even between different production batches of the same material. This assumption ignores the variability of materials in different batches and may lead to unstable machining behavior. In addition, traditional systems are difficult to detect and identify the material properties of machined products, resulting in the inability to dynamically adjust machining parameters according to actual situations. Without effective monitoring means to identify and feedback changes in material properties, the system will not be able to adjust the machining process in a timely manner, which may lead to the accumulation of long-term machining errors and unstable workpiece quality.

[0004] Therefore, there are defects in the prior art and improvements are needed. Summary of the Invention

[0005] [[ID='19']]To solve one or several problems in the prior art, the main purpose of this application is to provide a method and device for adaptively optimizing machining parameters based on workpiece recognition.

[0006] To achieve the above invention purpose, this application proposes a method for adaptively optimizing machining parameters based on workpiece recognition, and the method includes:

[0007] When a machining instruction is received, obtain multi-source feature information of the workpiece to be machined, where the multi-source feature information includes material data and structural data;

[0008] Match the preset process knowledge base according to the multi-source feature information to generate initial machining parameters and process target data;

[0009] Obtain dynamic state data during the machining process in real time, where the dynamic state data includes change parameters of the workpiece and feedback parameters of the machining equipment;

[0010] Based on the dynamic state data, analyze whether there is a deviation between the dynamic state data and the process target data;

[0011] When there is a deviation between the dynamic state data and a preset process target, generate adjustment parameters according to the dynamic state data.

[0012] The embodiment of the present application further provides a machining parameter adaptive optimization device based on workpiece recognition, including:

[0013] A first acquisition module, configured to acquire multi-source feature information of a workpiece to be machined when receiving a machining instruction, where the multi-source feature information includes material data and structure data;

[0014] A matching module, configured to match a preset process knowledge base according to the multi-source feature information to generate initial machining parameters and process target data;

[0015] A second acquisition module, configured to acquire dynamic state data during the machining process in real time, where the dynamic state data includes change parameters of the workpiece and feedback parameters of the machining equipment;

[0016] An analysis module, configured to analyze whether there is a deviation between the dynamic state data and the process target data based on the dynamic state data;

[0017] A generation module, configured to generate adjustment parameters according to the dynamic state data when there is a deviation between the dynamic state data and a preset process target.

[0018] The present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the method described in any one of the above when executing the computer program.

[0019] The present application further provides a computer-readable storage medium, on which a computer program is stored, and the computer program implements the steps of the method described in any one of the above when executed by a processor.

[0020] The method and device for adaptively optimizing machining parameters based on workpiece recognition according to the embodiments of the present application can comprehensively understand the attributes of the workpiece to be machined by obtaining multi-source feature information including material data and structural data, and generate initial machining parameters in combination with the process knowledge base, effectively ensuring the accuracy and stability of the machining process. During the machining process, the workpiece change parameters and equipment feedback parameters are obtained in real time, which can dynamically monitor the machining state and timely detect and identify deviations. By comparing with the preset process target data, the existence of deviations can be accurately identified, and then necessary adjustment measures can be taken. When there is a deviation between the dynamic state data and the preset target data, this method can generate adjustment parameters based on real-time data and automatically correct the deviations in the machining process. This adaptive adjustment mechanism can continuously optimize the parameters during the machining process and avoid unstable factors caused by human intervention. Automatically identifying problems and adjusting machining parameters throughout the machining process reduces the dependence on manual operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 is a schematic flow chart of a method for adaptively optimizing machining parameters based on workpiece recognition according to an embodiment of the present application;

[0022] Figure 2 is a schematic flow chart of a method for adaptively optimizing machining parameters based on workpiece recognition according to an embodiment of the present application;

[0023] Figure 3 is a schematic block diagram of the structure of a device for adaptively optimizing machining parameters based on workpiece recognition according to an embodiment of the present application;

[0024] Figure 4 is a schematic block diagram of the structure of a computer device according to an embodiment of the present application.

[0025] The realization, functional features and advantages of the purpose of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0027] Refer to Figure 1 , in the embodiments of the present application, a method for adaptively optimizing machining parameters based on workpiece recognition is provided, and the method includes:

[0028] S1. When a machining instruction is received, obtain multi-source feature information of the workpiece to be machined, where the multi-source feature information includes material data and structural data;

[0029] S2. Match the preset process knowledge base according to the multi-source feature information to generate initial processing parameters and process target data;

[0030] S3. Real-time obtain dynamic state data during the processing, where the dynamic state data includes change parameters of the workpiece and feedback parameters of the processing equipment;

[0031] S4. Based on the dynamic state data, analyze whether there is a deviation between the dynamic state data and the process target data;

[0032] S5. If there is a deviation between the dynamic state data and the preset process target, generate adjustment parameters according to the dynamic state data.

[0033] As described in the above steps S1 - S3, prepare for the subsequent processing process by obtaining the multi-source feature information of the workpiece. Through material data (such as hardness, density, ductility, etc.) and structure data (such as geometric shape, size, tolerance requirements, etc.), the system can provide a personalized processing plan for each workpiece. Material data helps the system understand the physical properties of the workpiece, while structure data provides the geometric requirements of the workpiece. Ensure that the system can fully understand various characteristics of the workpiece before starting processing, and avoid using a one-size-fits-all approach. This measure effectively improves the flexibility and accuracy of the system, and helps to enhance the adaptability and precision of the subsequent processing process. Match the obtained multi-source feature information of the workpiece with the preset process knowledge base. The process knowledge base usually contains a large amount of processing experience, material properties, processing methods, tool selection, cutting parameters, etc. By matching this knowledge, the system can automatically generate initial processing parameters (such as cutting speed, feed rate, etc.) and process target data (such as surface roughness, dimensional accuracy, etc.) according to the characteristics of the workpiece. By intelligently matching the knowledge base, the efficiency and correctness of the processing process can be ensured. It enables the system to select the optimal processing strategy according to the specific situation of the workpiece, avoiding errors and unreasonable selections in manually setting parameters, thereby improving production efficiency and product quality. Real-time monitor the dynamic data during the processing, mainly including change parameters of the workpiece (such as temperature, stress, surface roughness, etc.) and feedback parameters of the processing equipment (such as tool wear status, vibration, load, etc.). The real-time monitoring of the dynamic state data can reflect the actual situation during the processing, and help the system quickly identify potential problems. By obtaining and monitoring these dynamic state data in real time, the system can give real-time feedback on abnormal situations or deviations during the processing, providing a basis for the next adjustment. This step ensures that the system can adapt to changes during the processing, and avoids quality problems caused by ignoring dynamic situations.

[0034] As described in the above steps S4 - S5, by analyzing the deviation between the dynamic state data and the process target data, the system can determine whether the current machining process meets the preset target. If a certain parameter during the machining process (such as the temperature of the workpiece, surface roughness, etc.) deviates from the process target, the system can identify potential machining problems. This analysis usually uses data analysis algorithms or models for deviation detection, such as machine learning models, statistical analysis methods, etc. This analysis ensures the stability and accuracy of the machining process. If a deviation is found, the system can respond in a timely manner and take measures to adjust the machining process to avoid the final product not meeting the quality standards or causing waste of resources. In this way, the system can greatly reduce the rework and losses caused by poor machining. Once a deviation between the dynamic state data and the process target is detected, the system generates adjustment parameters based on these deviations. The adjustment parameters can include modifying the cutting speed, feed rate, coolant flow rate, etc., or adjusting certain working states of the equipment. These adjustments are made according to the real - time feedback data, aiming to correct the deviation and ensure that the machining process returns to the predetermined process target. By automatically generating and implementing the adjustment parameters, the system can make adaptive adjustments to ensure that the machining process is always stable and efficient. This process eliminates the need for manual intervention, making the production process more automated and intelligent, and can quickly optimize the machining effect under real - time feedback, improving the adaptive ability and efficiency of the production line.

[0035] As described above, by obtaining multi - source feature information including material data and structural data, the attributes of the workpiece to be machined can be comprehensively understood, and initial machining parameters can be generated in combination with the process knowledge base, effectively ensuring the accuracy and stability of the machining process. During the machining process, by obtaining the workpiece change parameters and equipment feedback parameters in real time, the machining state can be dynamically monitored, and deviations can be discovered and identified in a timely manner. By comparing with the preset process target data, the existence of deviations can be accurately identified, and then necessary adjustment measures can be taken. When there is a deviation between the dynamic state data and the preset target data, this method can generate adjustment parameters based on the real - time data and automatically correct the deviation during the machining process. This adaptive adjustment mechanism can continuously optimize the parameters during the machining process, avoiding unstable factors caused by human intervention. Automatically identifying problems and adjusting machining parameters throughout the machining process reduces the dependence on manual operations, thereby improving production efficiency, reducing the possibility of human errors, and optimizing the machining process. By matching the process knowledge base and adjusting parameters in combination with real - time dynamic data, this method can adapt to the machining requirements of different materials and structures, has high process flexibility and adaptability, and can cope with complex and variable machining environments.

[0036] Refer to Figure 2 , in one embodiment, based on the dynamic state data, analyzing whether the dynamic state data deviates from a preset process target, the method includes:

[0037] S41. Preprocess the change parameters of the workpiece, and extract the workpiece deformation characteristics and surface quality characteristics from the preprocessed change parameters;

[0038] S42. Compare the deformation characteristics and surface quality characteristics with the process target data item by item, and calculate the comprehensive deviation value according to the comparison results. The comprehensive deviation value is obtained by weighted calculation of the deformation characteristics and surface quality characteristics;

[0039] S43. Determine whether the comprehensive deviation value exceeds the preset tolerance range;

[0040] S44. When the comprehensive deviation value exceeds the preset tolerance range, it is determined that there is a deviation in the change parameters of the workpiece.

[0041] As described in the above steps, during the machining process, the changing parameters of the workpiece are obtained. Since the obtaining methods may include the detection signals of images or sensors, there will be various factors that affect them (such as temperature, pressure, stress, etc.). These changing parameters themselves may have noise or do not fully meet the machining objectives. Therefore, preprocessing is required. The preprocessing process usually includes denoising, smoothing, standardization, etc., in order to extract the features that have an actual impact on the final machining quality. Preprocessing is to reduce the noise and interference in the original data and improve the accuracy of feature extraction. The workpiece deformation features (such as elastic deformation, plastic deformation, etc.) and surface quality features (such as surface roughness, finish, etc.) are the key factors affecting the machining quality. Only after preprocessing can the extracted features truly reflect the machining state of the workpiece and avoid interference factors from affecting subsequent analysis and decision-making. The extracted deformation features and surface quality features will be compared item by item with the preset process target data. The process target data usually includes the expected deformation range and surface quality requirements, etc. Through this item-by-item comparison, the system can calculate the deviation between each feature and the target data. These deviations are summarized through a certain calculation method to obtain a comprehensive deviation value. The item-by-item comparison can ensure that each key feature (deformation and surface quality) can be evaluated separately, and it can accurately identify whether each feature meets the process objectives. The calculation of the comprehensive deviation value is to synthesize the deviation results of different features to form an overall quality evaluation value, enabling the system to balance among multiple factors. This item-by-item comparison method can accurately quantify the differences of each feature, enabling the system to more carefully identify the sources of deviations during the machining process and improve the overall control and prediction ability of product quality. The comprehensive deviation value provides a quantitative basis for subsequent adjustment decisions. In the actual machining process, the deformation features and surface quality features may have different importance for the final quality of the workpiece. For example, for some workpieces with high-precision machining, the surface quality may be more important than the deformation; while for some workpieces with large loads, the deformation features may be more critical. Therefore, by performing a weighted calculation on the deformation features and surface quality features, their contributions to the comprehensive deviation value can be adjusted according to their different degrees of influence on the machining objectives. The weighted calculation is to more truly reflect the actual impact of each feature on the final machining quality. Through weighted processing, the system can assign higher or lower weights to specific features according to different process requirements, thereby more accurately measuring the machining deviation of the workpiece. Judge the comprehensive deviation value to see if it exceeds the preset tolerance range. The tolerance range is set according to the process requirements and the workpiece usage standards, representing that the workpiece is still qualified within the allowable error range. If the deviation value exceeds the tolerance range, it means that the quality of the workpiece has exceeded the acceptable error range and must be adjusted. Judging whether the comprehensive deviation value exceeds the tolerance range is a key step in ensuring the machining quality. It defines the upper limit of the tolerated error. Once the deviation exceeds this range, the adjustment mechanism can be immediately triggered.The tolerance range is usually set based on process standards to ensure that the actual machining state of the workpiece will not affect the function and performance of the final product. This step can ensure that the machining process is always under control, can promptly identify abnormal conditions during the machining process, and avoid quality problems. If the deviation exceeds the limit, the system will be able to quickly take measures for adjustment to prevent the production of unqualified products. When the comprehensive deviation value exceeds the tolerance range, it means that there are problems in the machining process of the workpiece, which may result in the quality of the workpiece not meeting the requirements. At this time, the system will determine that there are deviations in the change parameters of the workpiece (such as deformation, surface quality, etc.), and perform corresponding processing based on this result, such as adjusting machining parameters, pausing machining, etc. By setting this "exceeding the limit" determination mechanism, the system can quickly respond to abnormalities in the machining process and prevent unqualified workpieces from entering the downstream process or leaving the factory. The timely response to determine that there are deviations in the change parameters of the workpiece can reduce the later rework cost or scrap rate and ensure production efficiency and product quality.

[0042] In one embodiment, based on the dynamic state data, analyzing whether the dynamic state data deviates from a preset process target, the method further includes:

[0043] Preprocessing the feedback parameters of the processing equipment, and extracting the equipment load characteristics and tool state characteristics from the preprocessed feedback parameters;

[0044] Comparing the equipment load characteristics and tool state characteristics item by item with the process target data, and calculating a comprehensive overlimit value according to the comparison result, the comprehensive overlimit value is obtained through weighted calculation of the equipment load characteristics and tool state characteristics;

[0045] Judging whether the comprehensive overlimit value exceeds a preset safety range;

[0046] When the comprehensive overlimit value exceeds the preset safety range, it is determined that there are deviations in the feedback parameters of the processing equipment.

[0047] As described above, the feedback parameters of the processing equipment may contain noise, abnormal data, or unnecessary information. To improve the accuracy and reliability of data analysis, these feedback parameters must be preprocessed. This may include methods such as noise removal, data normalization, and smoothing. Through the preprocessed data, features that have a greater impact on the process can be more precisely extracted. The process target data is usually a pre-set standard value, representing an ideal processing state. Comparing the equipment load characteristics and tool state characteristics item by item with these process target data helps to detect whether the current processing process meets the expected goals. Through this comparison, potential problems such as overloading and tool wear can be discovered in a timely manner. The result of the comparison can reflect the deviation between the current state of the equipment and the tool and the ideal state, helping to identify potential problems and adjust the processing parameters or take maintenance measures in a timely manner to avoid failures or quality problems. The comprehensive overlimit value is obtained through weighted calculation of the equipment load characteristics and tool state characteristics, which means that different characteristics may have different degrees of influence on the overall process target. For example, changes in equipment load may have a more significant impact on the processing process than tool state, so a higher weight can be given to the equipment load characteristics during calculation. The purpose of weighted calculation is to make the comprehensive overlimit value more accurately reflect the key problems in the processing process. Through weighting, it can be ensured that the comprehensive overlimit value better meets the actual processing requirements, thus having a better ability to identify abnormal states or failures of the equipment. The safety range is a predetermined threshold used to judge whether the processing process is safe and normal. If the comprehensive overlimit value exceeds this range, it indicates that the load of the equipment or the state of the tool has deviated from the predetermined safety range, which may affect the processing quality or the long-term operation of the equipment. Judging whether the comprehensive overlimit value exceeds the safety range helps to identify abnormalities in the equipment or tool in a timely manner and avoid failures or processing quality problems. This is also an important means for real-time monitoring of the health of the processing equipment and processing accuracy. By comparing with the preset safety range, when the comprehensive overlimit value exceeds the safety range, the system will consider that the feedback parameters of the equipment have deviated from the normal operating range, which may be caused by reasons such as excessive equipment load or tool wear. This judgment triggers further alarm or adjustment operations. This judgment can help to discover deviation problems in the equipment or processing process in a timely manner and provide corrective measures, such as adjusting equipment parameters, replacing tools, etc., so as to avoid possible equipment damage or poor processing during the production process.

[0048] In one embodiment, after the step of obtaining multi-source feature information of the workpiece to be processed, the method further includes:

[0049] When the material data of the multi-source feature information is missing, obtaining the geometric features and wall thickness distribution features of the structural data;

[0050] Performing similarity matching of the geometric features with similar structure workpieces in historical processing data;

[0051] Based on the matching results, obtain a set of candidate material types;

[0052] Input the wall thickness distribution characteristics into a preset prediction model, and use the prediction model to predict and output the predicted value of the material elastic modulus;

[0053] Select the material type with the highest processing difficulty from the set of candidate material types, use the standard process parameters of the selected material type as the reference parameters, and apply a safety correction to the reference parameters according to the reliability level of the predicted value of the material elastic modulus;

[0054] Mark the corrected parameters as the initial parameters of the prediction mode.

[0055] As described above, when the material data in the acquired multi-source feature information is missing, it means that predictions cannot be directly made based on the specific properties of the material (such as elastic modulus, hardness, etc.). Therefore, as an alternative, the geometric features and wall thickness distribution features of the structural data are acquired. These two features, namely the geometric features and the wall thickness distribution, directly reflect the structural complexity and morphology of the workpiece. In particular, the wall thickness distribution has an important impact on the machining difficulty and cutting force. Through these features, it is possible to help determine the approximate type of material or its machining difficulty, even without explicit material data. When complete material data is lacking, useful information can still be obtained through the structural features, ensuring that the system can still make reasonable predictions in the case of incomplete information. By using the data of the workpieces that have been processed in the historical machining data, workpieces similar to the current workpiece in terms of geometric features (such as shape, size, wall thickness, etc.) are found. This matching can help infer the possible material type and machining difficulty of the current workpiece. By finding workpieces with similar structures in the historical data, the machining experience and known material types of these similar workpieces can be referred to. This method utilizes the idea of big data to infer the characteristics of unknown workpieces through similarity. By matching workpieces with similar structures, the possible material type of the current workpiece can be inferred with the help of historical data, reducing the guesswork error caused by missing material data. The speculation of machining difficulty is more accurate, effectively avoiding the uncertainty when dealing with completely unknown workpieces. Through the matching results with workpieces with similar structures in the historical data, a set of possible material type sets are inferred. These material types are inferred based on the known data of workpieces with similar structures and may be consistent with the material of the current workpiece. Through logical reasoning and data matching, a set of possible material types are screened out as the candidate set for the subsequent steps, avoiding selecting materials completely based on experience or speculation. This enables the system to still effectively perform machining process prediction in the case of missing material data. The wall thickness distribution has a greater impact on the machining characteristics of the material. Especially during the cutting process, the parts with larger wall thickness may face greater stress, affecting the performance of the elastic modulus. Through a preset prediction model (such as a model based on machine learning, regression analysis, etc.), the wall thickness distribution feature is used to predict the elastic modulus of the material. Although there is no direct material data, the wall thickness distribution is related to the mechanical properties of the material, and the elastic modulus of the material can be approximately calculated through the model. Select the material type with the highest machining difficulty: After obtaining the set of candidate material types, select the material type with the highest machining difficulty among them to ensure the reliability of the machining process. Materials with high machining difficulty usually require more precise and conservative machining settings. For the selected high-difficulty material, select its standard process parameters (such as cutting speed, feed rate, etc.) as the benchmark to ensure process stability even in uncertain situations. Ensure that the selected process parameters can adapt to possible complex situations, prevent problems from occurring during the machining process, and provide a conservative strategy.By selecting the material type with the highest processing difficulty, the system can optimize the most challenging scenarios when facing unknown or uncertain materials, thereby enhancing processing safety. The reliability level of the predicted elastic modulus reflects the accuracy of the prediction result. If the prediction result is relatively reliable, process parameters close to the standard can be used; if the prediction is unreliable, the reference parameters need to be corrected. According to the reliability of the elastic modulus prediction, a correction factor is applied to the process parameters to provide higher safety when the prediction is inaccurate. For example, if the predicted value is uncertain, the feed rate and cutting speed can be appropriately reduced to prevent processing problems. In cases of high uncertainty, by applying safety corrections to the process parameters, the fault tolerance of the system can be improved, ensuring a stable and controllable processing process. This ensures that even when the prediction is unreliable, the process parameters can still be safely adjusted to avoid potential risks during processing. Marking the corrected process parameters as initial parameters means that these parameters will be used as the starting reference points in subsequent processing. These corrected initial parameters will serve as the benchmark during the processing to ensure stable control at all stages. Ensuring that the processing can start based on the corrected initial parameters, thereby avoiding problems caused by inaccurate initial settings.

[0056] In one embodiment, after the step of obtaining multi-source feature information of the workpiece to be processed, the method further includes:

[0057] When the material data of the multi-source feature information is a composite material, obtain the component feature information, interface characteristics, and interlayer distribution characteristics of the composite material;

[0058] Input the interface characteristics and interlayer distribution characteristics into a preset composite material processing performance prediction model, and use the prediction model to predict and output the delamination risk level;

[0059] Determine the cutting path according to the component feature information, determine the range of cutting speed and feed rate according to the delamination risk level, and set a real-time parameter exploration mechanism for the range of cutting speed and feed rate to increase the cutting speed and feed rate according to the completion progress of the cutting path;

[0060] Determine the initial processing parameters in combination with the real-time parameter exploration mechanism, cutting path, cutting speed, and feed rate.

[0061] As mentioned above, composite materials are usually composed of different components (such as fibers and matrix), and the distribution of these components in the material, interface characteristics (such as adhesiveness), and interlayer distribution (such as mechanical property differences between layers) all have important impacts on the processing performance. Obtaining this information helps to better understand the structure and characteristics of composite materials. Component characteristic information includes fiber type, matrix material, fiber arrangement direction, and density, etc. These characteristics determine the mechanical properties of the material, such as strength, hardness, and wear resistance. Interface characteristics refer to the bonding quality, interface strength, etc. between different components in the composite material, which affect the overall stability of the material and the mechanical response during cutting. The interlayer distribution characteristics describe the distribution, thickness, strength, etc. of each layer in the composite material, which are crucial for the delamination phenomenon and processing performance that may occur during the processing. By obtaining these characteristic information, the internal structure of the composite material can be comprehensively understood, providing data support for the subsequent processing process, and ensuring that possible processing problems can be accurately controlled and predicted during the processing. During the processing of composite materials, interface characteristics and interlayer distribution characteristics are the key factors leading to the risk of delamination. Prediction models are usually based on historical data and processing experience, and by analyzing the relationship between the characteristics of the material and the processing results, they predict possible risks. For example, weak interface bonding or uneven interlayer distribution may cause delamination of the material during processing. Based on the interface and interlayer characteristics of the composite material, the model can evaluate the probability of the material delaminating under different processing conditions and output a risk level. By predicting the delamination risk level, possible problems that may occur during the processing can be identified in advance, and corresponding measures (such as adjusting cutting parameters) can be taken to avoid or reduce risks and improve the stability and accuracy of processing. Cutting path: The component characteristics of composite materials directly affect the mechanical behavior during cutting, especially under the hardness and structural differences of different layers. The best cutting path can be designed through component characteristic information to avoid excessive wear and improve processing efficiency. Cutting speed and feed rate: According to the delamination risk level, the selection of cutting speed and feed rate becomes particularly important. A high-risk delamination level usually means that a lower cutting speed and a lower feed rate are required to reduce the impact force and thermal stress on the material during cutting and reduce material damage; while a lower delamination risk allows for a higher cutting speed and feed rate. Adjusting the cutting path, speed, and feed rate according to the characteristics of the material and risk prediction helps to optimize the processing quality during processing, reduce losses during processing, and improve processing efficiency at the same time. The design of the real-time parameter exploration mechanism is based on dynamically adjusting the cutting parameters during the processing. As the processing progresses, according to the completion of the cutting path, the cutting speed and feed rate are gradually increased. This mechanism can intelligently adapt to the actual situation during processing, avoid prematurely increasing the cutting speed resulting in unstable processing, and at the same time improve the cutting efficiency when the processing progress permits. When different parts of the processing have been completed and there is no delamination risk, it indicates that the stability of the material is relatively high. At this time, the cutting speed and feed rate can be gradually increased.The main effect of this mechanism is to improve the processing efficiency, reduce excessive conservatism in unnecessary cutting processes, reasonably increase the processing speed and accuracy, and at the same time ensure the stability and quality during the processing. After obtaining the ranges of the cutting path, cutting speed, and feed rate, the real-time parameter exploration mechanism synthesizes various information and finally determines the initial processing parameters. This step ensures that all processing parameters can be within a suitable range at the initial stage of processing and can be continuously optimized and adjusted according to the actual processing process. In this way, the initial processing parameters can be reasonably adjusted according to the characteristics of the composite material and the processing progress, so as to ensure the best balance between processing quality and efficiency and reduce waste and errors during the processing.

[0062] In one embodiment, after the step of generating adjustment parameters according to the dynamic state data when there is a deviation between the dynamic state data and the preset process target, the method further includes:

[0063] Obtain the dynamic state data set, and analyze the deviation pattern according to the dynamic state data set, where the deviation model includes continuous deviation, mutation deviation, and periodic deviation;

[0064] Generate an adjustment strategy according to the deviation model.

[0065] As described above, the dynamic state dataset refers to various data collected in real-time during the machining process, such as temperature, cutting force, vibration, surface quality, etc. These data reflect the real-time state of the machining process and can indicate whether the current machining is proceeding smoothly according to the preset goals. During the machining process, multiple factors may affect the machining quality, such as temperature changes, cutting force fluctuations, etc. The dynamic state dataset can provide real-time feedback during the machining process to help determine whether there are deviations in the process. During the machining process, deviations usually manifest as differences from the preset process goals. Analyzing the deviation pattern is to process the collected dynamic state data to identify the change patterns in the data, thereby understanding the types of deviations. Different types of deviations require different adjustment strategies. For example, continuous deviations usually require long-term adjustment of machining parameters, while sudden deviations may require immediate remedial measures. Periodic deviations may require optimizing the periodic interference factors during the machining process. By analyzing the deviation pattern, the types of deviations can be clearly identified, providing a clear direction for subsequent adjustment strategies, avoiding blind adjustments, and ensuring the stability of the machining process. Distinguishing different types of deviations helps quickly locate the root cause of the problem and take corresponding adjustment measures according to the characteristics of the deviations. For example, continuous deviations may require adjusting the machining conditions, while sudden deviations may require immediately stopping the machine to check the equipment or materials. By establishing a deviation model, different types of deviations can be identified and classified more systematically, providing a basis for formulating specific adjustment strategies. This can more efficiently solve problems in the machining process and improve production efficiency and machining quality. After identifying different types of deviations, corresponding adjustment strategies need to be formulated according to the characteristics of the deviations. Specifically: Usually, it is necessary to eliminate the deviation source by adjusting process parameters (such as cutting speed, feed rate, etc.) or performing equipment maintenance. Sudden deviations often require immediate emergency measures, such as adjusting the machining speed, pausing the machining for inspection, or replacing materials. Periodic deviations may require optimizing the cycle period during the machining process or adjusting the working frequency of the equipment to reduce the periodic impact. Different types of deviations require different adjustment strategies, and targeted adjustment of the parameters during the machining process can solve problems more effectively. For example, for continuous deviations, the process parameters can be gradually adjusted and corrected; while sudden deviations require rapid emergency measures to prevent further deterioration.

[0066] In one embodiment, the steps of generating an adjustment strategy according to the deviation model include:

[0067] When the deviation model is a continuous deviation, adopt progressive parameter adjustment;

[0068] When the deviation model is a sudden deviation, trigger protective load reduction and reduce the cutting depth in a preset manner;

[0069] When the deviation model is a periodic deviation, identify the deviation pattern of the dynamic state dataset, and dynamically avoid the flutter frequency according to the deviation pattern;

[0070] Based on the execution result of the adjustment strategy, record the effective adjustment strategy and the corresponding working condition characteristics;

[0071] When the same type of deviation appears repeatedly, preferentially call the historical successful solutions.

[0072] As described above, continuous deviation refers to the long-term and stable deviation of a certain parameter (such as cutting force, temperature, etc.) from the preset process target during the processing. For example, the deviation caused by long-term wear of the equipment, changes in environmental temperature, etc. In this case, adopting progressive parameter adjustment means gradually adjusting the relevant process parameters to make them gradually return to the preset target. Progressive adjustment usually makes small changes to avoid possible adverse effects caused by excessive one-time adjustment. This process can help avoid over-adjustment, ensure a smooth transition of the processing process, and reduce the negative impact on the processing quality. Progressive adjustment can avoid new problems caused by excessive correction, especially when there is a long-term and stable deviation. During the actual processing, rapid or drastic adjustment may lead to process instability. Therefore, progressive adjustment helps to find a balance point, gradually optimize the process, and avoid large fluctuations. It can smoothly adjust the continuous deviation in the processing process, avoid large fluctuations in the processing process, and ensure the stability of the process. The elimination and improvement of long-term deviation can improve production efficiency and extend the service life of the equipment. Mutant deviation refers to a drastic and rapid deviation that occurs during the processing. For example, factors such as equipment failure, unqualified materials, and operation errors may cause sudden deviations during the processing. At this time, by triggering protective load reduction, that is, quickly reducing parameters such as cutting depth, it can effectively prevent equipment damage or further deterioration of the processing process. The purpose of protective load reduction is to avoid overload by reducing the processing load (such as reducing the cutting depth), thereby protecting the equipment and reducing the negative impact brought by sudden deviations. Mutant deviations are usually unpredictable and have serious impacts. Therefore, when such deviations occur, rapid and effective emergency measures should be taken. The load reduction operation is an effective means to reduce the risks of the equipment and the processing process, especially when facing large fluctuations occurring in a short period of time. By reducing the processing load, problems such as equipment damage and increased tool wear can be prevented, ensuring that the processing process will not cause more problems due to sudden deviations. It enhances the safety of the processing process and equipment protection, and reduces production interruptions caused by mutant deviations. Periodic deviation refers to the deviation that repeatedly appears within a certain period. For example, phenomena such as periodic vibration and thermal expansion of mechanical equipment. This kind of deviation may cause chatter, that is, unstable vibration occurs during the processing, affecting the processing quality. After identifying the law of periodic deviation, the chatter frequency can be dynamically avoided, that is, by adjusting the processing parameters (such as cutting speed, feed rate, etc.), to avoid the working frequency from coinciding with the natural vibration frequency of the equipment, thereby avoiding resonance. Chatter is a common problem in the processing process, and once it occurs, it will lead to a decline in the processing surface quality, increased equipment wear, and reduced processing efficiency. By dynamically avoiding the chatter frequency, the negative impact of vibration on the processing process can be effectively avoided, and the damage to the equipment and workpiece can be reduced. Through dynamic adjustment, chatter caused by periodic deviation is avoided, and the unstable factors in the processing process are reduced. After each adjustment strategy is executed, the specific content and results of the adjustment need to be recorded.This includes adjustment strategies (such as gradual adjustment, protective load reduction, etc.) and the working condition characteristics at that time (such as temperature, pressure, cutting depth, etc.). These records provide valuable historical data for future reference in dealing with similar problems. The accumulation of data can improve the intelligence level of the system, making the adjustment strategy more accurate and efficient. It enhances the adaptive ability of the system and provides a basis for optimizing the machining process. When the same type of deviation reappears, the system can preferentially call the historical successful solutions, that is, the adjustment strategies that have been proven effective before. This can quickly respond and solve problems, avoid re-analyzing and designing adjustment strategies, and save time.

[0073] Referring to Figure 3 , an embodiment of the present application further provides a machining parameter adaptive optimization device based on workpiece recognition, including:

[0074] The first acquisition module 1 is used to acquire multi-source feature information of the workpiece to be machined when receiving a machining instruction, where the multi-source feature information includes material data and structure data;

[0075] The matching module 2 is used to match a preset process knowledge base according to the multi-source feature information to generate initial machining parameters and process target data;

[0076] The second acquisition module 3 is used to acquire dynamic state data during the machining process in real time, where the dynamic state data includes change parameters of the workpiece and feedback parameters of the machining equipment;

[0077] The analysis module 4 is used to analyze whether there is a deviation between the dynamic state data and the process target data based on the dynamic state data;

[0078] The generation module 5 is used to generate adjustment parameters according to the dynamic state data when there is a deviation between the dynamic state data and the preset process target.

[0079] As described above, it can be understood that each component of the machining parameter adaptive optimization device based on workpiece recognition proposed in the present application can implement the functions of any one of the machining parameter adaptive optimization methods based on workpiece recognition as described above, and the specific structure will not be elaborated.

[0080] Referring to Figure 4 , an embodiment of the present application further provides a computer device, which may be a server, and its internal structure may be as Figure 4As shown in the figure. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Among them, the processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device is used to store data such as monitoring data. The network interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements a method for adaptively optimizing machining parameters based on workpiece recognition.

[0081] The above-mentioned processor executes the above-mentioned method for adaptively optimizing machining parameters based on workpiece recognition, including: when receiving a machining instruction, obtaining multi-source feature information of the workpiece to be machined, where the multi-source feature information includes material data and structural data; matching a preset process knowledge base according to the multi-source feature information to generate initial machining parameters and process target data; obtaining dynamic state data during the machining process in real time, where the dynamic state data includes change parameters of the workpiece and feedback parameters of the machining equipment; based on the dynamic state data, analyzing whether there is a deviation between the dynamic state data and the process target data; if there is a deviation between the dynamic state data and the preset process target, generating adjustment parameters according to the dynamic state data.

[0082] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements a method for adaptively optimizing machining parameters based on workpiece recognition, including the steps of: when receiving a machining instruction, obtaining multi-source feature information of the workpiece to be machined, where the multi-source feature information includes material data and structural data; matching a preset process knowledge base according to the multi-source feature information to generate initial machining parameters and process target data; obtaining dynamic state data during the machining process in real time, where the dynamic state data includes change parameters of the workpiece and feedback parameters of the machining equipment; based on the dynamic state data, analyzing whether there is a deviation between the dynamic state data and the process target data; if there is a deviation between the dynamic state data and the preset process target, generating adjustment parameters according to the dynamic state data.

[0083] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium provided in this application and used in the embodiments can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0084] It should be noted that in this article, the terms "include", "comprise", or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, device, article, or method including a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, device, article, or method. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, device, article, or method including that element.

[0085] The above are only the preferred embodiments of this application, and do not limit the patent scope of this application accordingly. Any equivalent structural or equivalent process transformation made by using the content of the specification and drawings of this application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of this application.

Claims

1. An adaptive optimization method for machining parameters based on workpiece recognition, characterized in that The method includes: When a processing instruction is received, obtaining multi-source feature information of the workpiece to be processed, where the multi-source feature information includes material data and structural data; Matching a preset process knowledge base according to the multi-source feature information to generate initial processing parameters and process target data; Obtaining dynamic state data during the processing in real time, where the dynamic state data includes change parameters of the workpiece and feedback parameters of the processing equipment; Based on the dynamic state data, analyzing whether there is a deviation between the dynamic state data and the process target data; When there is a deviation between the dynamic state data and the preset process target, generating adjustment parameters according to the dynamic state data.

2. The machining parameter adaptive optimization method based on workpiece recognition according to claim 1, wherein Regarding the analysis of whether there is a deviation between the dynamic state data and the preset process target based on the dynamic state data, the method includes: Preprocessing the change parameters of the workpiece, and extracting workpiece deformation characteristics and surface quality characteristics from the preprocessed change parameters; Comparing the deformation characteristics and surface quality characteristics with the process target data item by item, and calculating a comprehensive deviation value according to the comparison results, where the comprehensive deviation value is obtained by weighted calculation of the deformation characteristics and surface quality characteristics; Judging whether the comprehensive deviation value exceeds a preset tolerance range; When the comprehensive deviation value exceeds the preset tolerance range, it is determined that there is a deviation in the change parameters of the workpiece.

3. The machining parameter adaptive optimization method based on workpiece recognition according to claim 2, wherein Regarding the analysis of whether there is a deviation between the dynamic state data and the preset process target based on the dynamic state data, the method further includes: Preprocessing the feedback parameters of the processing equipment, and extracting equipment load characteristics and tool state characteristics from the preprocessed feedback parameters; Comparing the equipment load characteristics and tool state characteristics with the process target data item by item, and calculating a comprehensive overlimit value according to the comparison results, where the comprehensive overlimit value is obtained by weighted calculation of the equipment load characteristics and tool state characteristics; Judging whether the comprehensive overlimit value exceeds a preset safety range; When the comprehensive overlimit value exceeds the preset safety range, it is determined that there is a deviation in the feedback parameters of the processing equipment.

4. The machining parameter adaptive optimization method based on workpiece recognition according to claim 1, characterized in that After the step of obtaining the multi-source feature information of the workpiece to be processed, the method further includes: When the material data of the multi-source feature information is missing, obtaining the geometric characteristics and wall thickness distribution characteristics of the structural data; Performing similarity matching on the geometric characteristics with similar structure workpieces in historical processing data; Based on the matching results, obtaining a set of candidate material types; Inputting the wall thickness distribution characteristics into a preset prediction model, and predicting and outputting a predicted value of the material elastic modulus through the prediction model; Selecting the material type with the highest processing difficulty from the set of candidate material types, taking the standard process parameters of the selected material type as the reference parameters, and applying a safety correction to the reference parameters according to the reliability level of the predicted value of the material elastic modulus; Marking the corrected parameters as the initial parameters of the prediction mode.

5. The machining parameter adaptive optimization method based on workpiece recognition according to claim 4, characterized in that After the step of obtaining the multi-source feature information of the workpiece to be processed, the method further includes: When the material data of the multi-source feature information is a composite material, obtaining the component feature information, interface characteristics and interlayer distribution characteristics of the composite material; Input the interface characteristics and interlayer distribution characteristics into a preset prediction model for the processing performance of composite materials, and use the prediction model to predict and output the delamination risk level; Determine the cutting path according to the component characteristic information, determine the range of cutting speed and feed rate according to the delamination risk level, and set a real-time parameter exploration mechanism for the range of cutting speed and feed rate, which is used to increase the cutting speed and feed rate according to the completion progress of the cutting path; Determine the initial processing parameters by combining the real-time parameter exploration mechanism, cutting path, cutting speed and feed rate.

6. The machining parameter adaptive optimization method based on workpiece recognition according to claim 1, characterized in that After the step of generating adjustment parameters according to the dynamic state data when the dynamic state data deviates from the preset process target, the method further includes: Obtain the dynamic state data set, and analyze the deviation pattern according to the dynamic state data set, where the deviation model includes continuous deviation, mutation deviation and periodic deviation; Generate an adjustment strategy according to the deviation model.

7. The machining parameter adaptive optimization method based on workpiece recognition according to claim 6, characterized in that The step of generating an adjustment strategy according to the deviation model includes: When the deviation model is a continuous deviation, adopt a progressive parameter adjustment; When the deviation model is a mutation deviation, trigger a protective load reduction and reduce the cutting depth in a preset manner; When the deviation model is a periodic deviation, identify the deviation law of the dynamic state data set, and dynamically avoid the chatter frequency according to the deviation law; Based on the execution result of the adjustment strategy, record the effective adjustment strategy and the corresponding working condition characteristics; When the same type of deviation appears repeatedly, preferentially call the historical successful solution.

8. An adaptive optimization device for machining parameters based on workpiece recognition, characterized in that, including: A first acquisition module, configured to acquire multi-source characteristic information of a workpiece to be processed when receiving a processing instruction, where the multi-source characteristic information includes material data and structural data; A matching module, configured to match a preset process knowledge base according to the multi-source characteristic information, and generate initial processing parameters and process target data; A second acquisition module, configured to acquire dynamic state data during the processing in real time, where the dynamic state data includes change parameters of the workpiece and feedback parameters of the processing equipment; An analysis module, configured to analyze whether the dynamic state data deviates from the process target data based on the dynamic state data; A generation module, configured to generate adjustment parameters according to the dynamic state data when the dynamic state data deviates from a preset process target.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images