Dynamic optimization method and system for metal tool drilling process

Abstract

This invention discloses a dynamic optimization method and system for the drilling process of metal tools, relating to the field of precision manufacturing. The method includes: acquiring basic drilling information; collecting laser point cloud data of the target drill bit, analyzing the drill bit wear state, and generating the drill bit wear state; performing drilling control analysis to generate optimal drilling parameters, performing dynamic spatial mapping of the work area, and generating a reference drilling dynamic particle space; performing dynamic monitoring of the work space and generating a dynamic monitoring dataset; performing drilling defect probability identification and generating a first predicted probability; if the first predicted probability is greater than a preset probability, optimizing the optimal drilling parameters until the output predicted probability meets the preset probability. This invention solves the technical problem of existing drilling control methods lacking precise control and dynamic monitoring of the drilling process, leading to the inability to timely detect and predict drilling defects. It achieves the technical effect of effectively avoiding drilling defects through precise control and dynamic monitoring of the drilling process.

Description

Technical Field

[0001] This application relates to the field of precision manufacturing, and in particular to a method and system for dynamic optimization of the drilling process of metal tools. Background Technology

[0002] In the metalworking industry, drilling is a crucial process widely used in the fabrication and repair of various metal workpieces. Due to the diversity and complexity of metal materials, and the numerous variable factors involved in the drilling process, such as drill bit wear, workpiece material, drilling location, depth, and diameter, the drilling process becomes complex and difficult to control precisely. This leads to drilling defects, such as excessively large hole diameter, rough hole walls, and hole misalignment. Most existing drilling methods rely on traditional empirical parameter settings or simple feedback control systems for drilling control. These methods often depend on the operator's experience and skill level, making it difficult to achieve precise control of the drilling process and to adjust drilling parameters in a timely manner according to the actual condition of the drill bit, resulting in inconsistent drilling quality.

[0003] At present, the drilling control of metal tools suffers from a lack of precise control and dynamic monitoring of the drilling process, resulting in the inability to detect and predict drilling defects in a timely manner. Summary of the Invention

[0004] This application provides a dynamic optimization method and system for the metal tool drilling process. It employs techniques such as generating optimal drilling parameters by combining basic drilling information and drill bit wear status, generating a benchmark drilling dynamic particle space based on these parameters, comparing the benchmark dynamic particle space with a dynamic monitoring dataset from the actual drilling process to identify drilling defect probabilities, and performing continuous dynamic spatial correction to ensure the predicted probability meets a preset probability. This addresses the technical problem of existing drilling control methods lacking precise control and dynamic monitoring of the drilling process, leading to the inability to timely detect and predict drilling defects. The system effectively avoids drilling defects through precise control and dynamic monitoring of the drilling process.

[0005] This application provides a dynamic optimization method for the drilling process of metal tools, comprising: acquiring basic drilling information of the metal workpiece to be processed, including workpiece material information, drilling position information, drilling depth information, and drilling diameter information; acquiring laser point cloud data and performing drill wear analysis on the target drill bit to generate drill wear state; performing drilling control analysis based on the basic drilling information and the drill wear state to generate optimal drilling parameters and perform dynamic spatial mapping of the operation to generate a reference drilling dynamic particle space; when drilling is controlled according to the optimal drilling parameters, simultaneously starting a micro-integrated module to perform dynamic monitoring of the operation space of the target drill bit to generate a dynamic monitoring dataset; comparing the reference drilling dynamic particle space and the dynamic monitoring dataset to identify the probability of drilling defects and generate a first predicted probability; if the first predicted probability is greater than a preset probability, optimizing the optimal drilling parameters and performing continuous dynamic spatial correction until the output predicted probability meets the preset probability.

[0006] In a possible implementation, drilling control analysis is performed by combining the basic drilling information and the drill bit wear state to generate optimal drilling parameters and perform dynamic space mapping for operation, generating a benchmark drilling dynamic particle space. The following processes are then performed: determining whether the drill bit wear state has reached a preset replacement state; if not, using the drill bit wear state and the basic drilling information as constraints, positive sample collection is conducted to obtain multiple sets of drilling parameter samples, where each set of drilling parameter samples includes feed rate timing samples, rotation speed timing samples, and cutting fluid feed timing samples; clustering the multiple sets of drilling parameter samples to generate multi-cluster drilling parameter samples; calculating drilling reliability based on the multi-cluster drilling parameter samples to generate multiple reliability indices; optimizing the multi-cluster drilling parameter samples with the goal of maximizing drilling efficiency, combining the multiple reliability indices, to generate the optimal drilling parameters; inputting the optimal drilling parameters into the dynamic space mapping module for dynamic space mapping for operation, generating the benchmark drilling dynamic particle space.

[0007] In a possible implementation, borehole reliability is calculated based on the multi-cluster borehole parameter samples to generate multiple reliability indices, and the following processing is performed: within a preset time zone, historical borehole quality samples are collected based on the multi-cluster borehole parameter samples to generate multiple borehole quality sample sets; the proportion of negative samples is calculated for the multiple borehole quality sample sets to generate the multiple reliability indices.

[0008] In a possible implementation, the optimal drilling parameters are input into a dynamic space mapping module to perform operational dynamic space mapping, generating the benchmark drilling dynamic particle space, and the following processing is performed: modeling data of the target drill bit is collected, and the dynamic space mapping module is constructed; operational space simulation of the optimal drilling parameters is performed using the dynamic space mapping module to generate the benchmark drilling dynamic particle space; wherein, the step of constructing the dynamic space mapping module includes: using the drill bit specifications of the target drill bit as constraints, collecting operational parameter sample sets, benchmark drill bit displacement time series sample sets, benchmark drill bit vibration state time series sample sets, benchmark drill bit temperature time series sample sets, and base... A time-series sample set of quasi-chip removal state is used; a dynamic displacement predictor is trained and constructed using the operating parameter sample set and the reference drill bit displacement time-series sample set; a dynamic vibration predictor is trained and constructed using the operating parameter sample set and the reference drill bit vibration state time-series sample set; a dynamic temperature predictor is trained and constructed using the operating parameter sample set and the reference drill bit temperature time-series sample set; a dynamic chip predictor is trained and constructed using the operating parameter sample set and the reference chip removal state time-series sample set; the dynamic displacement predictor, the dynamic vibration predictor, the dynamic temperature predictor, and the dynamic chip predictor are integrated to generate the dynamic space mapping module.

[0009] In a possible implementation, the following processing is performed: the micro-integrated module includes a micro-displacement sensor, a micro-vibration sensor, a micro-temperature sensor, and a high-precision image sensor; wherein the micro-displacement sensor, the micro-vibration sensor, and the micro-temperature sensor are located in the chip removal channel of the target drill bit, and the remaining space between the micro-displacement sensor, the micro-vibration sensor, and the micro-temperature sensor and the chip removal channel meets the chip removal requirements; the high-precision image sensor is located outside the target drill bit and is used for video monitoring of the drilling position, and the high-precision image sensor is connected to a chip state identifier; the chip state identifier is used to identify the number of chips discharged from the video data collected by the high-precision image sensor and generate the chip state monitoring time sequence.

[0010] In a possible implementation, borehole defect probability identification is performed by comparing the benchmark borehole dynamic particle space and the dynamic monitoring dataset to generate a first predicted probability. The following processing is then performed: using the benchmark borehole dynamic particle space as a reference, offset analysis is performed on the dynamic monitoring dataset to generate displacement offset index, vibration offset index, temperature offset index, and chip offset index; it is determined whether the displacement offset index, vibration offset index, temperature offset index, and chip offset index are greater than a preset offset threshold; if so, defect probability identification is performed based on the displacement offset index, vibration offset index, temperature offset index, and chip offset index to generate the first predicted probability.

[0011] In a possible implementation, the first prediction probability is generated by performing the following processing: performing offset consistency identification on the displacement offset index, the vibration offset index, the temperature offset index, and the chip offset index to generate a multidimensional offset consistency index; performing index set value identification on the displacement offset index, the vibration offset index, the temperature offset index, and the chip offset index; and generating the first prediction probability using the multidimensional offset consistency index and the index set value.

[0012] In a possible implementation, the optimal drilling parameters are optimized and continuously dynamically corrected in space until the output predicted probability meets the preset probability. Then, the following processing is performed: if the first predicted probability is greater than the preset probability, control response error analysis is performed on the target drill bit to generate a control response error direction; the optimal drilling parameters are adjusted according to the control response error direction with a preset step size, and the dynamic monitoring dataset is updated. Defect probability calculation and update are performed until the output predicted probability meets the preset probability.

[0013] This application also provides a dynamic optimization system for metal tool drilling processes, comprising: a drilling basic information acquisition module for acquiring drilling basic information of the metal workpiece to be processed, including workpiece material information, drilling position information, drilling depth information, and drilling diameter information; a drill bit wear analysis module for acquiring laser point cloud data and performing drill bit wear analysis on the target drill bit to generate a drill bit wear state; a drilling control analysis module for performing drilling control analysis by combining the drilling basic information and the drill bit wear state to generate optimal drilling parameters and perform dynamic space mapping of the work, generating a reference drilling dynamic particle space; a work space dynamic monitoring module for simultaneously starting a micro-integrated module to perform dynamic monitoring of the work space of the target drill bit when drilling is controlled according to the optimal drilling parameters, generating a dynamic monitoring dataset; a drilling defect probability identification module for comparing the reference drilling dynamic particle space and the dynamic monitoring dataset to identify drilling defect probabilities and generate a first predicted probability; and a dynamic space correction module for optimizing the optimal drilling parameters and performing continuous dynamic space correction if the first predicted probability is greater than a preset probability, until the output predicted probability meets the preset probability.

[0014] The proposed method and system for dynamic optimization of metal tool drilling process first acquires basic drilling information of the workpiece to be processed, including workpiece material information, drilling location information, drilling depth information, and drilling diameter information. Then, laser point cloud data acquisition and drill wear analysis are performed on the target drill bit to generate drill wear status. Subsequently, drilling control analysis is conducted by combining the basic drilling information and drill wear status to generate optimal drilling parameters. Finally, the optimal drilling parameters are mapped into a dynamic space to generate a reference drilling dynamic particle space. The optimal drilling parameters include feed rate timing, spindle speed timing, and coolant feed timing. The reference drilling dynamic particle space includes reference drill bit displacement timing and reference drill bit vibration timing. The benchmark drill bit temperature timing and benchmark chip removal status timing are used to control drilling according to the optimal drilling parameters. The target drill bit's micro-integrated module is activated to dynamically monitor the target drill bit's workspace, generating a dynamic monitoring dataset. The dynamic monitoring dataset includes drill bit displacement monitoring timing, drill bit vibration monitoring timing, drill bit temperature monitoring timing, and chip status monitoring timing. Then, based on the benchmark drill bit dynamic particle space and the dynamic monitoring dataset, drilling defect probability identification is performed to generate a first predicted probability. If the first predicted probability is greater than the preset probability, the optimal drilling parameters are optimized and continuous dynamic space correction is performed until the output predicted probability meets the preset probability. This achieves the technical effect of effectively avoiding drilling defects through precise control and dynamic monitoring of the drilling process. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments of the present invention will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the method according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0016] Figure 1 This is a flowchart illustrating the dynamic optimization method for metal tool drilling process provided in an embodiment of this application.

[0017] Figure 2 This is a schematic diagram of the process for generating optimal drilling parameters in the dynamic optimization method for metal tool drilling provided in the embodiments of this application.

[0018] Figure 3 This is a schematic diagram of the structure of the dynamic optimization system for the metal tool drilling process provided in an embodiment of this application.

[0019] Explanation of reference numerals in the attached diagram: 10 for borehole basic information acquisition module, 20 for drill bit wear analysis module, 30 for borehole control analysis module, 40 for working space dynamic monitoring module, 50 for borehole defect probability identification module, and 60 for dynamic space correction module. Detailed Implementation

[0020] 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.

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application will be provided in conjunction with the accompanying drawings. The described embodiments should not be considered as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] In the following description, references to "some embodiments" describe a subset of all possible embodiments. However, it is understood that "some embodiments" may be the same or different subsets of all possible embodiments and may be combined with each other without conflict. The terms "first" and "second" are used merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only.

[0023] This application provides a method for dynamic optimization of the metal tool drilling process, such as... Figure 1 As shown, the method includes:

[0024] Step S100: Obtain basic drilling information of the metal workpiece to be processed, including workpiece material information, drilling location information, drilling depth information, and drilling diameter information.

[0025] Specifically, the workpiece material information refers to the physical and chemical properties of the material used in the metal workpiece to be processed, such as material type, hardness, and toughness; the drilling location information refers to the specific location of the drill hole on the metal workpiece to be processed, determined by the design drawings; the drilling depth information refers to the distance from the surface of the metal workpiece to the bottom of the drill hole; and the drilling diameter information refers to the diameter of the drill bit, which determines the size of the drill hole. The diameter of the drill bit should be slightly smaller than or equal to the hole diameter required by the drawing to ensure the processing quality of the hole. Specifically, the specific material type, hardness, toughness, and other physical and chemical properties of the metal workpiece to be processed are determined by reviewing its technical documents, material specifications, or by conducting material tests; the precise location, number, and size of the drill holes are determined by reviewing the design drawings of the metal workpiece; the required drilling depth is obtained from the design drawings; and the diameter of the drill holes is determined from the design drawings.

[0026] Step S200: Perform laser point cloud data acquisition and drill bit wear analysis on the target drill bit to generate the drill bit wear status.

[0027] Specifically, the target drill bit is placed within the scanning range of a laser scanner, ensuring its entire surface is scanned. The laser scanner is then activated to perform a 3D scan of the target drill bit, acquiring point cloud data (a set of three-dimensional points representing the surface shape and features of the target drill bit). The obtained point cloud data is then denoised to remove noise points caused by environmental interference or equipment errors. The point cloud data is also smoothed to reduce minor fluctuations or errors generated during the scanning process. Point cloud data from a new drill bit or an unused drill bit (under ideal or standard conditions) is used as a baseline model. The point cloud data of the target drill bit is compared with the baseline model. The wear condition of the target drill bit is assessed by measuring changes in shape, volume, or key dimensions. Based on the comparative analysis, the wear amount of the target drill bit is calculated, which is a measure of the change in the target drill bit's shape or size, and may include indicators such as wear area and wear depth.

[0028] Step S300: Combine the basic drilling information and the wear state of the drill bit to perform drilling control analysis, generate optimal drilling parameters, perform dynamic space mapping of the operation, and generate a reference drilling dynamic particle space.

[0029] Specifically, based on workpiece material information, the hardness, toughness, and other properties of the material are analyzed to determine the appropriate range of cutting force and cutting speed. The wear condition of the drill bit is assessed to evaluate its impact on cutting force, cutting heat, and vibration, and cutting parameters are adjusted to compensate for wear. Taking into account the workpiece material, drilling location, depth, diameter, and drill bit wear condition, optimal drilling parameters are generated using empirical formulas, experimental data, or intelligent algorithms (such as machine learning and neural networks). These optimal drilling parameters refer to the combination of parameters that achieves the best drilling effect under given workpiece material and drill bit wear conditions, calculated through analysis. These parameters include feed rate sequence, spindle speed sequence, and coolant feed sequence. The feed rate sequence describes the change in the axial feed speed of the target drill bit over time during drilling; the spindle speed sequence describes the change in the rotational speed of the target drill bit over time during drilling; and the coolant feed sequence describes the change in the speed and timing of coolant supply over time during drilling. The coolant is used to cool the drill bit, lubricate the cutting area, and flush away chips.

[0030] Based on optimal drilling parameters, a benchmark drilling dynamic particle space model is established to simulate the drilling process. This model is used to predict and simulate the dynamic behavior of the target drill bit during drilling. Within the benchmark model, benchmark drill bit displacement time sequences, drill bit vibration state time sequences, drill bit temperature time sequences, and chip removal state time sequences are defined. These time sequences represent the behavioral characteristics of the target drill bit under ideal conditions and serve as reference benchmarks for drilling monitoring and prediction. Specifically, the benchmark drill bit displacement time sequence is a reference sequence showing the axial feed displacement of the target drill bit over time within the benchmark drilling dynamic particle space; the benchmark drill bit vibration state time sequence is a reference sequence showing the vibration generated by the target drill bit during drilling over time within the benchmark drilling dynamic particle space; the benchmark drill bit temperature time sequence is a reference sequence showing the temperature of the target drill bit over time during drilling within the benchmark drilling dynamic particle space; and the benchmark chip removal state time sequence is a reference sequence showing the chip removal situation over time within the benchmark drilling dynamic particle space.

[0031] like Figure 2As shown, in one possible implementation, step S300 further includes step S310, determining whether the drill bit wear state has reached a preset replacement state. If not, using the drill bit wear state and the drilling basic information as constraints, positive example samples are collected to obtain multiple sets of drilling parameter samples. Each set of drilling parameter samples includes feed rate timing samples, rotational speed timing samples, and cutting fluid feed timing samples. Specifically, based on the drill bit wear state generated in step S200, it is checked whether it has reached a preset replacement standard. If the drill bit wear state has not reached the preset replacement standard, using the current drill bit wear state and drilling basic information as constraints, multiple sets of drilling parameter samples are collected from past successful drilling operations as positive example samples. Positive example samples refer to parameter combinations where the drilling operation was successful and the drilling quality met requirements. Step S320 involves clustering the multiple sets of drilling parameter samples to generate multi-cluster drilling parameter samples. Specifically, the collected multiple sets of borehole parameter samples are preprocessed, such as through data cleaning and standardization. Clustering algorithms (such as K-means, hierarchical clustering, etc.) are then used to cluster the preprocessed data, generating multiple clusters of borehole parameter samples, each cluster representing a group of similar borehole parameter combinations. Step S330 involves calculating borehole reliability based on the multiple clusters of borehole parameter samples, generating multiple reliability indices. Specifically, appropriate reliability indices are determined according to the actual situation of the drilling operation, such as drilling accuracy, drill bit life, and surface roughness. For each cluster of borehole parameter samples, the corresponding historical drilling result data is used for reliability evaluation, generating corresponding reliability indices. Step S340 involves optimizing the multiple clusters of borehole parameter samples with the goal of maximizing drilling efficiency, combining the multiple reliability indices to generate the optimal borehole parameters. Specifically, maximizing drilling efficiency is used as the objective function for optimization, where drilling efficiency can be measured through multiple dimensions such as drilling time and drilling quality. By combining multiple reliability indicators, a multi-objective optimization algorithm (such as genetic algorithm, particle swarm optimization algorithm, etc.) is used to optimize multiple clusters of drilling parameter samples to find the optimal drilling parameters that can meet both reliability requirements and maximize drilling efficiency. In step S350, the optimal drilling parameters are input into a dynamic space mapping module to perform dynamic space mapping for the operation, generating the reference drilling dynamic particle space. Specifically, the optimal drilling parameters are input into the dynamic space mapping module, which generates a reference drilling dynamic particle space describing various dynamic characteristics of the target drill bit during operation, based on the optimal drilling parameters and the actual situation of the drilling operation (such as the shape of the metal workpiece to be processed, the position of the fixture, etc.). The reference drilling dynamic particle space contains time-series data of dynamic information such as drill bit displacement, vibration, and temperature. This implementation method fully utilizes successful experience from historical data, making the generated optimal drilling parameters closer to actual operational needs, ensuring both drilling quality and efficiency, and achieving the technical effect of improving the accuracy of obtaining optimal drilling parameters.

[0032] In one possible implementation, step S330 further includes step S331, which involves collecting historical borehole quality samples based on the multiple clusters of borehole parameter samples within a preset time zone to generate multiple borehole quality sample sets. Specifically, a preset time interval is defined for extracting borehole quality samples from historical data. This time interval can be long enough to include sufficient historical data to evaluate the reliability of the borehole parameters. For each cluster of borehole parameter samples, within the preset time zone, historical records of drilling using that cluster of borehole parameters are searched. Data related to borehole quality, such as borehole diameter deviation, borehole wall roughness, and borehole roundness, are extracted from the found historical records. The extracted borehole quality data is then categorized according to the corresponding borehole parameter sample cluster to form multiple borehole quality sample sets. Each borehole quality sample set represents the borehole quality performance of a cluster of borehole parameter samples within the preset time zone. Step S332 involves calculating the proportion of negative samples in the multiple borehole quality sample sets to generate the multiple reliability indices. Specifically, in drilling operations, negative examples refer to samples where the drilling quality is substandard, meaning the drilling results do not meet the preset quality standards. For each set of drilling quality samples, the proportion of negative examples to the total number of samples in that set is calculated. This proportion represents the drilling reliability index of that cluster of drilling parameters within a preset time zone. This calculation is performed for each cluster of drilling parameter samples to generate a corresponding reliability index. This implementation method, by collecting data within a preset time zone, comprehensively considers the performance of drilling parameters under different time periods and operating conditions, achieving a more comprehensive and accurate reliability assessment.

[0033] In one possible implementation, step S350 further includes step S351, collecting modeling data of the target drill bit and constructing the dynamic space mapping module. Specifically, detailed data of the target drill bit, including dimensions, shape, and material properties, is collected through physical measurements, simulation experiments, CAD drawings, etc. This modeling data is used to construct the dynamic space mapping module. Based on the characteristics of the target drill bit and operational requirements, a suitable mathematical or physical model is selected to construct the dynamic space mapping module. The dynamic space mapping module is a mathematical or physical model used to simulate the dynamic behavior of the target drill bit in the working space. Step S352 involves using the dynamic space mapping module to simulate the optimal drilling parameters in the working space, generating the benchmark drilling dynamic particle space. Specifically, the optimal drilling parameters are input into the dynamic space mapping module. Based on the optimal drilling parameters and the initial conditions of the dynamic space mapping module, the simulation environment is initialized, the dynamic space mapping module is run, and the dynamic behavior of the target drill bit in the working space is simulated, including the trajectory, velocity, acceleration, etc. Data generated during the simulation, such as drill bit position, attitude, and force conditions, are recorded. The data generated during the simulation is processed and analyzed to extract key information. Based on the processed data, a three-dimensional benchmark drilling dynamic particle space is constructed to describe the dynamic behavior of the target drill bit during the operation.

[0034] The construction of the dynamic space mapping module, step S350, further includes: step S351, using the drill bit specifications of the target drill bit as constraints, collecting a set of operating parameters, a set of time-series samples of reference drill bit displacement, a set of time-series samples of reference drill bit vibration, a set of time-series samples of reference drill bit temperature, and a set of time-series samples of reference chip discharge status. Specifically, the specifications of the target drill bit are determined, including parameters such as the drill bit's size, shape, and material. A series of operating parameter data under different operating conditions (such as different rotational speeds and feed rates) are collected. These data describe the basic operating conditions of the target drill bit during operation. Under the operating conditions included in the set of operating parameters, corresponding time-series samples are collected. The reference drill bit displacement time-series sample records the actual displacement data of the target drill bit during operation; the reference drill bit vibration status time-series sample records the vibration data of the target drill bit during operation; the reference drill bit temperature time-series sample records the temperature change of the target drill bit during operation; and the reference chip discharge status time-series sample records data on the chip discharge status, such as the shape, size, and discharge speed of the chips. Step S352: A dynamic displacement predictor is trained and constructed using the operation parameter sample set and the reference drill bit displacement time series sample set. Step S353: A dynamic vibration predictor is trained and constructed using the operation parameter sample set and the reference drill bit vibration state time series sample set. Step S354: A dynamic temperature predictor is trained and constructed using the operation parameter sample set and the reference drill bit temperature time series sample set. Step S355: A dynamic chip predictor is trained and constructed using the operation parameter sample set and the reference chip discharge state time series sample set. Specifically, the collected sample sets are preprocessed, including cleaning, standardization, and feature extraction, to improve data quality and model training effectiveness. Based on the characteristics and requirements of the problem, a suitable machine learning or deep learning model is selected to construct the predictor. For example, neural networks, support vector machines (SVM), random forests, and other algorithms can be used. Each predictor is trained using the preprocessed operation parameter sample set and the corresponding time series sample set (such as displacement, vibration, temperature, and chip discharge state). The performance of the predictor is optimized by adjusting the model parameters and structure. Step S356: Integrate the dynamic displacement predictor, dynamic vibration predictor, dynamic temperature predictor, and dynamic chip predictor to generate the dynamic spatial mapping module. Specifically, the trained dynamic displacement predictor, dynamic vibration predictor, dynamic temperature predictor, and dynamic chip predictor are integrated into a unified framework to form the dynamic spatial mapping module. The dynamic spatial mapping module can simultaneously predict the displacement, vibration, temperature, and chip discharge status of the target drill bit based on the input operating parameters. This implementation method constructs the dynamic spatial mapping module by training multiple predictors, achieving simultaneous prediction of multiple states of the target drill bit, and thus improving the accuracy and reliability of the dynamic spatial mapping of the operation.

[0035] Step S400: When drilling is controlled according to the optimal drilling parameters, the micro integrated module is simultaneously started to dynamically monitor the working space of the target drill bit and generate a dynamic monitoring dataset.

[0036] Specifically, the dynamic monitoring of the workspace refers to the real-time monitoring of various dynamic data of the target drill bit during operation using sensors, including displacement, vibration, and temperature, to assess the status and performance of the drilling operation and to promptly identify and resolve problems. Specifically, based on the optimal drilling parameters (including feed rate timing, rotational speed timing, and coolant feed timing), the control parameters of the drilling equipment or machine tool are adjusted, and the drilling equipment or machine tool is started to perform drilling operations on the metal workpiece to be processed according to the optimal drilling parameters. A micro-integrated module is then activated to monitor the various dynamic data of the target drill bit's workspace in real time. This micro-integrated module is a miniaturized device integrating multiple sensors and data processing units, used for real-time monitoring of the target drill bit's workspace dynamic data. Installed on or near the target drill bit, it can acquire key information such as the drill bit's displacement, vibration, and temperature in real time. The displacement data of the target drill bit is recorded in real time by displacement sensors in the micro-integrated module, generating a drill bit displacement monitoring time series to reflect the actual position and movement trajectory of the target drill bit during the drilling process. Vibration sensors monitor the vibration of the target drill bit in real time, recording vibration data and generating a drill bit vibration monitoring time series to evaluate the stability and cutting quality of the target drill bit. Temperature sensors monitor the temperature of the target drill bit in real time, generating a drill bit temperature monitoring time series to reflect the thermal load and heat dissipation of the target drill bit. Vision sensors or other appropriate sensors monitor chip generation and removal, generating a chip state monitoring time series to reflect the stability and cutting effect of the cutting process. The dynamic monitoring data collected by the micro-integrated module is then processed to generate a dynamic monitoring dataset.

[0037] In one possible implementation, step S400 further includes step S410, where the micro-integrated module includes a micro-displacement sensor, a micro-vibration sensor, a micro-temperature sensor, and a high-precision image sensor; step S420, where the micro-displacement sensor, the micro-vibration sensor, and the micro-temperature sensor are located in the chip removal channel of the target drill bit, and the remaining space between the micro-displacement sensor, the micro-vibration sensor, and the micro-temperature sensor and the chip removal channel meets the chip removal requirements; step S430, where the high-precision image sensor is located outside the target drill bit and is used for video monitoring of the drilling position, and the high-precision image sensor is connected to a chip state identifier; step S440, where the chip state identifier is used to identify the number of chips discharged from the video data collected by the high-precision image sensor and generate the chip state monitoring time sequence.

[0038] Specifically, the micro displacement sensor is used to monitor minute displacement changes of the target drill bit during drilling, thereby assessing the stability and cutting force of the target drill bit; the micro vibration sensor is used to detect vibrations generated by the target drill bit during cutting, reflecting the stability of the cutting process and potential cutting problems; the micro temperature sensor is used to monitor temperature changes of the target drill bit and its surrounding environment, as temperature changes affect cutting efficiency and drill bit life; the high-precision image sensor is used to capture high-definition video images of the drilling position, providing data support for chip state identification. The chip removal channel is a channel inside the target drill bit used to remove chips (waste) generated during cutting. The micro displacement sensor, micro vibration sensor, and micro temperature sensor are installed within the chip removal channel to ensure that these sensors can directly contact the chips and heat generated during cutting, thereby obtaining more accurate data. The remaining space between these sensors and the chip removal channel needs to meet chip removal requirements, i.e., it should not affect the normal discharge of chips. A high-precision image sensor is mounted on the outside of the target drill bit to clearly capture the drilling location and chip removal status. The high-precision image sensor is connected to a chip condition identifier via data cable or wirelessly, enabling real-time transmission of video data for processing. The chip condition identifier receives video data from the high-precision image sensor and preprocesses it, such as through noise reduction and enhancement. Using image processing algorithms, it identifies features such as the quantity, size, and shape of chips in the video, assesses the chip removal status and efficiency, and records the identified chip condition information chronologically to form a chip condition monitoring timeline. This implementation, by integrating a micro-module and a chip condition identification system, achieves comprehensive monitoring and control of the drilling process, effectively improving the accuracy of dynamic monitoring of the workspace.

[0039] Step S500: Compare the benchmark borehole dynamic particle space and the dynamic monitoring dataset to identify borehole defects and generate a first predicted probability.

[0040] Specifically, the benchmark borehole dynamic particle space represents the dynamic feature space of normal drilling operations and serves as the benchmark and reference for borehole defect probability identification. The dynamic monitoring dataset reflects real-time dynamic information during the drilling operation. Necessary preprocessing, such as data cleaning, noise filtering, and feature extraction, is performed on the dynamic monitoring dataset to ensure data quality and consistency. The preprocessed dynamic monitoring dataset is then compared with the benchmark borehole dynamic particle space. By comparing the differences between the actual monitoring data and the benchmark data, any anomalies or deviations from the normal range are identified. Based on the comparison results, appropriate algorithms or models (such as machine learning models, statistical models, etc.) are used to identify the probability of borehole defects. This borehole defect probability reflects the likelihood of defects (such as drill breakage, borehole wall damage, borehole wall roughness, borehole diameter being too large or too small, borehole position deviation, etc.) occurring under the current drilling operation conditions. The result of the borehole defect probability identification is output as a first predicted probability, which is a quantitative indicator used to assess the risk level of the current drilling operation.

[0041] In one possible implementation, step S500 further includes step S510, which involves performing offset analysis on the dynamic monitoring dataset based on the reference borehole dynamic particle space to generate displacement offset indices, vibration offset indices, temperature offset indices, and chip offset indices. Specifically, various parameters (displacement, vibration, temperature, and chip quantity) are extracted from the dynamic monitoring dataset, and these parameters are compared with the corresponding parameter ranges or patterns in the reference borehole dynamic particle space. The differences or offsets between each parameter and the reference values ​​are calculated to generate corresponding offset indices. Step S520 involves determining whether the displacement offset indices, vibration offset indices, temperature offset indices, and chip offset indices are greater than preset offset thresholds. Specifically, the preset offset thresholds are set based on historical data and experience and are used to determine whether the current drilling operation deviates from the normal range. Each offset index is compared to see if it exceeds its corresponding preset offset threshold. Step S530, if so, defect probability identification is performed based on the displacement offset indices, vibration offset indices, temperature offset indices, and chip offset indices to generate the first predicted probability. Specifically, when any one or more offset indicators exceed a preset offset threshold, it indicates that an anomaly or defect may have occurred in the drilling process. Based on the offset indicators exceeding the preset threshold, a preset algorithm or model (such as a machine learning model) calculates the probability of the defect and generates a first predicted probability. This implementation method quickly identifies any abnormal or deviating parameters through offset analysis. By calculating offset indicators, it quantitatively measures the difference or degree of deviation between the current drilling operation and the normal operation, which helps to more accurately determine whether there are potential problems in the drilling process, thus achieving the technical effect of improving the efficiency and accuracy of defect probability identification.

[0042] In one possible implementation, generating the first predicted probability, step S530 further includes step S531, which involves identifying the offset consistency of the displacement offset index, the vibration offset index, the temperature offset index, and the chip offset index to generate a multidimensional offset consistency index. Specifically, by comparing the relative magnitudes and trends of the offset indices, a consistency analysis is performed on the offset indices. If multiple indices show similar degrees of offset (i.e., all significantly exceeding or falling below the normal range), then offset consistency is considered to exist. Based on the results of the consistency analysis, a multidimensional offset consistency index is generated. This multidimensional offset consistency index can be a numerical value used to quantify the degree of consistency among multiple offset indices. Step S532 involves identifying the index clustering values ​​of the displacement offset index, the vibration offset index, the temperature offset index, and the chip offset index. Specifically, it involves identifying whether the offset indices exhibit a clustering trend, i.e., whether most indices deviate from the normal range. If most indices deviate from the normal range, then the clustering values ​​(such as the mean, median, etc.) of these offset indices are calculated to quantify the degree of this clustering trend. Step S533: Generate the first predicted probability using the multidimensional offset consistency index and the index set value. Specifically, combine the multidimensional offset consistency index and the index set value, and use a preset prediction model (such as a machine learning model, statistical model, etc.) as input to generate the first predicted probability. This implementation comprehensively evaluates the state of the drilling process by generating the multidimensional offset consistency index and the index set value, achieving the technical effect of accurately assessing whether the drilling process deviates from the normal state and improving the accuracy of the first predicted probability generation.

[0043] Step S600: If the first predicted probability is greater than the preset probability, optimize the optimal drilling parameters and perform continuous dynamic spatial correction until the output predicted probability satisfies the preset probability.

[0044] Specifically, the first predicted probability is compared with a preset probability threshold (i.e., a preset probability). This preset probability is a pre-defined threshold based on machining experience, safety standards, and other analyses, used to compare with the first predicted probability to determine whether further optimization or adjustment of operating parameters is needed. When the first predicted probability is greater than the preset probability, it indicates that the current optimal drilling parameters are not optimal and require further adjustment to reduce the probability of adverse factors occurring. This is achieved by using optimization algorithms (such as gradient descent, genetic algorithms, etc.) to adjust drilling parameters (e.g., adjusting feed rate, rotational speed, and coolant feed rate) to optimize the model or algorithm output, reducing the first predicted probability below the preset probability. During the optimization process, the dynamic monitoring dataset is updated based on the new drilling parameters, and steps S500 and S600 are repeated until the first predicted probability meets the preset probability, meaning the risk of drilling using the optimized drilling parameters has been reduced to an acceptable range. This application employs techniques such as combining basic drilling information and drill bit wear status to generate optimal drilling parameters, generating a benchmark drilling dynamic particle space based on the optimal drilling parameters, comparing the benchmark drilling dynamic particle space with the dynamic monitoring dataset during the actual drilling process to identify the probability of drilling defects, and performing continuous dynamic space correction to ensure that the predicted probability meets the preset probability. These techniques achieve the technical effect of effectively avoiding drilling defects through precise control and dynamic monitoring of the drilling process.

[0045] In one possible implementation, the optimal drilling parameters are optimized and continuously dynamically corrected until the output predicted probability meets the preset probability. Step S600 further includes step S610: if the first predicted probability is greater than the preset probability, control response error analysis is performed on the target drill bit to generate a control response error direction. Specifically, firstly, if the first predicted probability is greater than the preset probability, it indicates that the current drilling operation has a high risk of defects. By checking the difference between the control signal (such as rotational speed, feed rate, etc.) of the target drill bit and the actual response (which may be caused by drill bit wear, mechanical failure, or instability of the control system), control response error analysis is performed on the target drill bit. Based on the result of the control response error analysis, a control response error direction is generated. The control response error direction is used to indicate how to adjust the control parameters of the target drill bit to reduce the predicted probability of drilling defects. Step S620: according to the control response error direction, the optimal drilling parameters are adjusted with a preset step size, and the dynamic monitoring dataset is updated. Defect probability calculation is updated until the output predicted probability meets the preset probability. Specifically, based on the direction of the control response error, the optimal drilling parameters, including rotational speed, feed rate, and cutting fluid flow rate, are adjusted according to a preset step size. After parameter adjustment, the drilling process continues to be monitored, and new data is collected to update the dynamic monitoring dataset. Based on the new dynamic monitoring dataset, the defect probability is recalculated. The new predicted probability reflects the drilling process state after parameter adjustment. Step S620 is repeated continuously until the output predicted probability meets the preset probability. This iterative process continues to ensure that the drilling process remains under control and reduces the probability of defects. This implementation method, by optimizing and dynamically correcting the optimal drilling parameters, ensures that the drilling process always proceeds according to preset requirements, achieving the technical effects of reducing defect risk and improving drilling quality.

[0046] In the above text, refer to Figures 1-2 A dynamic optimization method for the metal tool drilling process according to embodiments of the present invention is described in detail. Next, reference will be made to... Figure 3 A dynamic optimization system for metal tool drilling process according to an embodiment of the present invention is described.

[0047] The dynamic optimization system for metal tool drilling process according to embodiments of the present invention addresses the technical problem of existing drilling control systems lacking precise control and dynamic monitoring of the drilling process, resulting in the inability to timely detect and predict drilling defects. The system achieves the technical effect of effectively avoiding drilling defects through precise control and dynamic monitoring of the drilling process. The dynamic optimization system for metal tool drilling process includes: a drilling basic information acquisition module 10, a drill bit wear analysis module 20, a drilling control analysis module 30, a working space dynamic monitoring module 40, a drilling defect probability identification module 50, and a dynamic space correction module 60.

[0048] The system includes: a drilling basic information acquisition module 10, used to acquire drilling basic information of the metal workpiece to be processed, including workpiece material information, drilling position information, drilling depth information, and drilling diameter information; a drill bit wear analysis module 20, used to collect laser point cloud data and analyze drill bit wear of the target drill bit to generate drill bit wear status; a drilling control analysis module 30, used to perform drilling control analysis by combining the drilling basic information and the drill bit wear status, generate optimal drilling parameters, and perform dynamic space mapping to generate a reference drilling dynamic particle space; a work space dynamic monitoring module 40, used to simultaneously start a micro-integrated module to perform dynamic monitoring of the work space of the target drill bit when drilling is controlled according to the optimal drilling parameters, and generate a dynamic monitoring dataset; a drilling defect probability identification module 50, used to compare the reference drilling dynamic particle space and the dynamic monitoring dataset to identify drilling defect probabilities and generate a first predicted probability; and a dynamic space correction module 60, used to optimize the optimal drilling parameters and perform continuous dynamic space correction if the first predicted probability is greater than a preset probability, until the output predicted probability meets the preset probability.

[0049] The specific configuration of the drilling control analysis module 30 will be described in detail below. As mentioned above, drilling control analysis is performed by combining the basic drilling information and the drill bit wear state to generate optimal drilling parameters and perform dynamic space mapping of the operation to generate a reference drilling dynamic particle space. The drilling control analysis module 30 may further include: a positive example sample acquisition unit used to determine whether the drill bit wear state has reached a preset replacement state. If not, positive example sample acquisition is performed with the drill bit wear state and the basic drilling information as constraints to obtain multiple sets of drilling parameter samples. Each set of drilling parameter samples includes feed rate timing samples, speed timing samples, and cutting fluid timing samples. The system includes: a feed timing sample; a clustering unit for clustering the multiple sets of borehole parameter samples to generate multiple clusters of borehole parameter samples; a borehole reliability calculation unit for calculating borehole reliability based on the multiple clusters of borehole parameter samples to generate multiple reliability indices; an optimization unit for optimizing the multiple clusters of borehole parameter samples with the goal of maximizing borehole efficiency, combined with the multiple reliability indices, to generate the optimal borehole parameters; and a job dynamic space mapping unit for inputting the optimal borehole parameters into a dynamic space mapping module to perform job dynamic space mapping and generate the benchmark borehole dynamic particle space.

[0050] The borehole reliability calculation unit, which calculates borehole reliability based on the multi-cluster borehole parameter samples and generates multiple reliability indices, may further include: a historical borehole quality sample collection subunit for collecting historical borehole quality samples based on the multi-cluster borehole parameter samples within a preset time zone to generate multiple borehole quality sample sets; and a negative sample proportion calculation subunit for calculating the negative sample proportion of the multiple borehole quality sample sets to generate the multiple reliability indices.

[0051] The optimal drilling parameters are input into a dynamic space mapping module for dynamic space mapping of the operation, generating the benchmark drilling dynamic particle space. The dynamic space mapping unit may further include: a modeling data acquisition subunit for acquiring modeling data of the target drill bit and constructing the dynamic space mapping module; and an operation space simulation subunit for simulating the operation space using the dynamic space mapping module on the optimal drilling parameters to generate the benchmark drilling dynamic particle space. The step of constructing the dynamic space mapping module includes: using the drill bit specifications of the target drill bit as constraints, acquiring a set of operation parameters, a time-series sample set of benchmark drill bit displacement, and a time-series sample set of benchmark drill bit vibration state. A dynamic displacement predictor is constructed by training a set of time-series samples of reference drill bit temperature and reference chip removal status; a dynamic vibration predictor is constructed by training a set of time-series samples of reference drill bit temperature and reference operation parameters; a dynamic chip predictor is constructed by training a set of time-series samples of reference operation parameters and reference drill bit vibration status; a dynamic temperature predictor is constructed by training a set of time-series samples of reference operation parameters and reference chip removal status; and a dynamic space mapping module is generated by integrating the dynamic displacement predictor, the dynamic vibration predictor, the dynamic temperature predictor, and the dynamic chip predictor.

[0052] The specific configuration of the workspace dynamic monitoring module 40 will be described in detail below. As mentioned above, the workspace dynamic monitoring module 40 may further include: the micro integrated module includes a micro displacement sensor, a micro vibration sensor, a micro temperature sensor, and a high-precision image sensor; wherein, the micro displacement sensor, the micro vibration sensor, and the micro temperature sensor are located in the chip removal channel of the target drill bit, and the remaining space between the micro displacement sensor, the micro vibration sensor, and the micro temperature sensor and the chip removal channel meets the chip removal requirements; the high-precision image sensor is located outside the target drill bit and is used for video monitoring of the drilling position, and the high-precision image sensor is connected to a chip state identifier; the chip state identifier is used to identify the number of chips discharged from the video data collected by the high-precision image sensor.

[0053] The specific configuration of the borehole defect probability identification module 50 will be described in detail below. As mentioned above, the borehole defect probability identification module 50 performs borehole defect probability identification by comparing the reference borehole dynamic particle space and the dynamic monitoring dataset to generate a first predicted probability. The borehole defect probability identification module 50 may further include: a offset analysis unit used to perform offset analysis on the dynamic monitoring dataset based on the reference borehole dynamic particle space to generate displacement offset index, vibration offset index, temperature offset index, and chip offset index; a judgment unit used to determine whether the displacement offset index, vibration offset index, temperature offset index, and chip offset index are greater than a preset offset threshold; and a defect probability identification unit used to perform defect probability identification based on the displacement offset index, vibration offset index, temperature offset index, and chip offset index if the value is greater than a preset offset threshold to generate the first predicted probability.

[0054] The defect probability identification unit, which generates the first predicted probability, may further include: an offset consistency identification subunit for performing offset consistency identification on the displacement offset index, the vibration offset index, the temperature offset index, and the chip offset index to generate a multidimensional offset consistency index; an index set value identification subunit for performing index set value identification on the displacement offset index, the vibration offset index, the temperature offset index, and the chip offset index; and a first predicted probability generation subunit for generating the first predicted probability using the multidimensional offset consistency index and the index set value.

[0055] The specific configuration of the dynamic space correction module 60 will be described in detail below. As mentioned above, the optimal drilling parameters are optimized and continuously dynamically corrected until the output predicted probability meets the preset probability. The dynamic space correction module 60 may further include: a control response error analysis unit used to perform control response error analysis on the target drill bit and generate a control response error direction if the first predicted probability is greater than the preset probability; and a defect probability calculation and update unit used to adjust the optimal drilling parameters according to the control response error direction with a preset step size, update the dynamic monitoring dataset, and perform defect probability calculation and update until the output predicted probability meets the preset probability.

[0056] The dynamic optimization system for metal tool drilling process provided in this embodiment of the invention can execute the dynamic optimization method for metal tool drilling process provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0057] Although this application makes various references to certain modules in the system according to the embodiments of this application, any number of different modules can be used and run on user terminals and / or servers. The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy distinction between each other and are not used to limit the scope of protection of this invention.

[0058] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application. In some cases, the actions or steps described in this application can be performed in a different order than that shown in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A method for dynamic optimization of a metal tool drilling process, characterized by, The method comprises: Obtaining drilling basic information of a metal workpiece to be processed, including workpiece material information, drilling position information, drilling depth information and drilling diameter information; Performing laser point cloud data collection and drill wear analysis on a target drill to generate a drill wear state; Performing drilling control analysis in combination with the drilling basic information and the drill wear state to generate optimal drilling parameters and perform job dynamic space mapping to generate a reference drilling dynamic particle space; When drilling is controlled according to the optimal drilling parameters, a micro integrated module is started synchronously to perform job space dynamic monitoring on the target drill to generate a dynamic monitoring data set; Comparing the reference drilling dynamic particle space and the dynamic monitoring data set to perform drilling defect probability identification to generate a first prediction probability; If the first prediction probability is greater than a preset probability, the optimal drilling parameters are optimized, and continuous dynamic space correction is performed until the output prediction probability meets the preset probability.

2. The dynamic optimization method for metal tool drilling process according to claim 1, wherein, Performing drilling control analysis in combination with the drilling basic information and the drill wear state to generate optimal drilling parameters and perform job dynamic space mapping to generate a reference drilling dynamic particle space, comprising: Judging whether the drill wear state reaches a preset replacement state, and if not, collecting positive example samples with the drill wear state and the drilling basic information as constraints to obtain a plurality of drilling parameter samples, wherein any drilling parameter sample includes a feed speed time sequence sample, a rotation speed time sequence sample, and a cutting fluid feed time sequence sample; Clustering the plurality of drilling parameter samples to generate a plurality of cluster drilling parameter samples; Performing drilling reliability calculation based on the plurality of cluster drilling parameter samples to generate a plurality of reliability indexes; Optimizing the plurality of cluster drilling parameter samples in combination with the plurality of reliability indexes to generate the optimal drilling parameters, with the goal of maximizing drilling efficiency; Inputting the optimal drilling parameters into a dynamic space mapping module to perform job dynamic space mapping to generate the reference drilling dynamic particle space.

3. The dynamic optimization method for metal tool drilling process according to claim 2, wherein, Performing drilling reliability calculation based on the plurality of cluster drilling parameter samples to generate a plurality of reliability indexes, comprising: Within a preset time zone, collecting historical drilling quality samples based on the plurality of cluster drilling parameter samples to generate a plurality of drilling quality sample sets; Calculating a negative example sample proportion of the plurality of drilling quality sample sets to generate the plurality of reliability indexes.

4. The method of claim 2, wherein the metal tool drilling process dynamic optimization method is characterized by, Inputting the optimal drilling parameters into a dynamic space mapping module to perform job dynamic space mapping to generate the reference drilling dynamic particle space, comprising: Collecting modeling data of the target drill to construct the dynamic space mapping module; Performing job space simulation on the optimal drilling parameters by the dynamic space mapping module to generate the reference drilling dynamic particle space; Wherein, the step of constructing the dynamic space mapping module comprises: Collecting job parameter sample sets, reference drill displacement time sequence sample sets, reference drill vibration state time sequence sample sets, reference drill temperature time sequence sample sets, and reference chip discharge state time sequence sample sets with the drill specifications of the target drill as constraints; Training and constructing a dynamic displacement predictor using the job parameter sample sets and the reference drill displacement time sequence sample sets; training and constructing a dynamic vibration predictor by using the operation parameter sample set and the benchmark bit vibration state time series sample set; training and constructing a dynamic temperature predictor by using the operation parameter sample set and the benchmark bit temperature time series sample set; training and constructing a dynamic chip predictor by using the operation parameter sample set and the benchmark chip discharge state time series sample set; integrating the dynamic displacement predictor, the dynamic vibration predictor, the dynamic temperature predictor and the dynamic chip predictor to generate the dynamic space mapping module.

5. The method of claim 1, wherein, The micro integrated module includes a micro displacement sensor, a micro vibration sensor, a micro temperature sensor and a high-precision image sensor; The micro displacement sensor, the micro vibration sensor and the micro temperature sensor are located in the chip removal channel of the target bit, and the remaining space between the micro displacement sensor, the micro vibration sensor and the micro temperature sensor and the chip removal channel meets the chip removal demand space. The high-precision image sensor is located outside the target bit and is used for video monitoring of the drilling position, and the high-precision image sensor is connected with a chip state identifier. The chip state identifier is used for chip discharge quantity identification of the video data collected by the high-precision image sensor.

6. The method of dynamic optimization of a metal tool drilling process of claim 1, wherein, Comparing the benchmark drilling dynamic particle space and the dynamic monitoring data set to identify the drilling defect probability and generate a first prediction probability, including: Taking the benchmark drilling dynamic particle space as a benchmark, performing offset analysis on the dynamic monitoring data set to generate displacement offset indicators, vibration offset indicators, temperature offset indicators and chip offset indicators; determining whether the displacement offset indicators, the vibration offset indicators, the temperature offset indicators and the chip offset indicators are greater than a preset offset threshold; If yes, identifying the defect probability based on the displacement offset indicators, the vibration offset indicators, the temperature offset indicators and the chip offset indicators to generate the first prediction probability.

7. The method of dynamic optimization of a metal tool drilling process of claim 6, wherein, Generating the first prediction probability includes: performing offset consistency identification on the displacement offset indicators, the vibration offset indicators, the temperature offset indicators and the chip offset indicators to generate multi-dimensional offset consistency indicators; performing index central value identification on the displacement offset indicators, the vibration offset indicators, the temperature offset indicators and the chip offset indicators; generating the first prediction probability based on the multi-dimensional offset consistency indicators and the index central values.

8. The method of dynamic optimization of a metal tool drilling process of claim 7, wherein, Optimizing the optimal drilling parameters and continuously correcting the dynamic space until the output prediction probability meets the preset probability, including: If the first prediction probability is greater than the preset probability, performing control response error analysis on the target bit to generate a control response error direction; adjusting the optimal drilling parameters by a preset step size according to the control response error direction, updating the dynamic monitoring data set, updating the defect probability calculation, and until the output prediction probability meets the preset probability.

9. A system for dynamic optimization of a metal tool drilling process, characterized by The system is used to implement the metal tool drilling process dynamic optimization method of any one of claims 1-8, and the system includes: The drilling foundation information acquisition module is configured to acquire drilling foundation information of a metal workpiece to be processed, including workpiece material information, drilling position information, drilling depth information and drilling diameter information. The drill wear analysis module is configured to perform laser point cloud data acquisition and drill wear analysis on the target drill, and generate a drill wear state. The drilling control analysis module is configured to perform drilling control analysis in combination with the drilling foundation information and the drill wear state, generate optimal drilling parameters, perform job dynamic space mapping, and generate a reference drilling dynamic particle space. The job space dynamic monitoring module is configured to, when drilling is controlled according to the optimal drilling parameters, synchronously start the micro integrated module to perform job space dynamic monitoring on the target drill, and generate a dynamic monitoring data set. The drilling defect probability identification module is configured to compare the reference drilling dynamic particle space and the dynamic monitoring data set to perform drilling defect probability identification, and generate a first prediction probability. The dynamic space correction module is configured to, if the first prediction probability is greater than a preset probability, optimize the optimal drilling parameters, and perform continuous dynamic space correction until the output prediction probability meets the preset probability.

Images