Fixture monitoring method and system for part machining

Abstract

The invention provides a clamp monitoring method and system for part machining, and relates to the technical field of clamp monitoring, and the method comprises the steps: determining a part clamping mode, and building a clamping database based on clamping dynamic characteristics; the training state memory unit comprises parallel state memory branches mapped to the part clamping mode; reading clamp monitoring data, preprocessing and screening point cloud distribution data; in combination with the target clamping mode, matching the target memory branch, performing dynamic characteristic analysis, and determining a first monitoring result; working condition eccentricity analysis based on the spatial position and clamp limiting is carried out, and a second monitoring result is determined; and taking the first monitoring result and the second monitoring result as a clamp monitoring result. According to the invention, the technical problems of poor monitoring accuracy and low intelligent degree caused by incomprehensive monitoring of workpiece processing conditions in different clamping modes and limitation in data processing in an existing clamp monitoring method are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of fixture monitoring, and in particular to a fixture monitoring method and system for parts processing. Background Art

[0002] In fields involving high-precision processing or high requirements for fixture stability, such as aerospace, automobile manufacturing, electronic equipment and other fields, the fixture is one of the key factors to ensure product processing accuracy and stability. However, traditional fixture monitoring methods still have some technical problems. On the one hand, existing fixture monitoring methods usually only focus on one or a few common clamping methods, which is difficult to meet the diverse clamping needs in the processing of different workpieces, resulting in incomplete monitoring of workpiece processing conditions under different clamping methods; on the other hand, existing fixture monitoring methods have limitations in data processing and mechanical analysis, and it is difficult to accurately analyze complex workpiece clamping conditions, which makes it difficult to cope with various changes in complex processing processes. Summary of the invention

[0003] The present application provides a fixture monitoring method and system for parts processing, aiming to solve the technical problems that existing fixture monitoring methods usually only consider one or a few clamping methods, resulting in incomplete monitoring of the processing conditions of workpieces under different clamping methods, and there are limitations in data processing, resulting in poor monitoring accuracy and low intelligence.

[0004] The first aspect disclosed in the present application provides a fixture monitoring method for part processing, the method comprising: determining a part clamping method, building a clamping database based on clamping dynamic characteristics, wherein the part clamping method includes at least mechanical clamping, hydraulic clamping, electromagnetic clamping, and vacuum adsorption clamping; based on the clamping database, training a state memory unit, wherein the state memory unit includes a parallel state memory branch mapped to the part clamping method; reading fixture monitoring data of a target part, pre-processing and screening point cloud distribution data, wherein the point cloud distribution data is based on the center of gravity of the part , with multi-level preset complementary step lengths and key points as distribution screening criteria; combined with the target clamping method, matching the target memory branch based on the state memory unit, performing dynamic characteristic analysis on the point cloud distribution data, and determining the first monitoring result; reading the part processing task and determining the eccentricity tolerance range, performing working condition eccentricity analysis based on the spatial position and the fixture limit, and determining the second monitoring result, wherein the working condition eccentricity includes the part clamping eccentricity and the relative eccentricity between the tool clamping part and the part clamping part; based on the first monitoring result and the second monitoring result, as the fixture monitoring result of the target part.

[0005] The second aspect disclosed in the present application provides a fixture monitoring system for part processing, the system is used for the above-mentioned fixture monitoring method for part processing, the system includes: a clamping database building module, the clamping database building module is used to determine the part clamping method, and build a clamping database based on the clamping dynamic characteristics, wherein the part clamping method at least includes mechanical clamping, hydraulic clamping, electromagnetic clamping, and vacuum adsorption clamping; a state memory unit training module, the state memory unit training module is used to train the state memory unit based on the clamping database, the state memory unit includes a parallel state memory branch mapped to the part clamping method; a point cloud distribution data screening module, the point cloud distribution data screening module is used to read the fixture monitoring data of the target part, pre-process and perform point cloud distribution data screening, wherein the point The cloud distribution data is based on the center of gravity of the part, and is used as a distribution screening standard with multi-level preset complementary steps and key points; a dynamic characteristic analysis module, which is used to combine the target clamping method, match the target memory branch based on the state memory unit, and perform dynamic characteristic analysis on the point cloud distribution data to determine the first monitoring result; a working condition eccentricity analysis module, which is used to read the part processing task and determine the eccentricity tolerance range, perform working condition eccentricity analysis based on spatial position and fixture limit, and determine the second monitoring result, wherein the working condition eccentricity includes the part clamping eccentricity and the relative eccentricity based on the tool clamping part and the part clamping part; a fixture monitoring result acquisition module, which is used to use the first monitoring result and the second monitoring result as the fixture monitoring result of the target part.

[0006] According to a third aspect disclosed in the present application, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, any step of the first aspect disclosed in the present application is implemented.

[0007] The fourth aspect disclosed in the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any step of the first aspect disclosed in the present application.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: By integrating various clamping methods such as mechanical clamping, hydraulic clamping, electromagnetic clamping, and vacuum adsorption clamping, the applicable scope and monitoring accuracy of the monitoring system are improved; by training the state memory unit, which includes parallel state memory branches mapped to different clamping methods, effective identification and matching of different clamping states are achieved, and the intelligence of the monitoring system is improved; by point cloud distribution data screening and dynamic characteristics analysis, accurate monitoring and analysis of the workpiece clamping conditions are achieved, providing a reliable basis for subsequent regulation and optimization; by working condition eccentricity analysis and clamp limit-based regulation, effective monitoring and regulation of part clamping eccentricity and relative eccentricity between the tool clamping part and the part clamping part are achieved, and processing accuracy and stability are improved. In summary, the fixture monitoring method for part processing effectively solves the limitations of existing fixture monitoring methods by integrating multiple clamping methods, applying state memory units, point cloud data screening and dynamic characteristics analysis, as well as working condition eccentricity analysis and fixture regulation and control, and improves the intelligence, accuracy and stability of the fixture monitoring system.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic flow chart of a fixture monitoring method for parts processing provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a fixture monitoring system for parts processing provided in an embodiment of the present application; Figure 3 This is a diagram of the internal structure of a computer device provided in an embodiment of the present application.

[0011] Explanation of the accompanying drawings: clamping database building module 10, state memory unit training module 20, point cloud distribution data screening module 30, dynamic characteristic analysis module 40, working condition eccentricity analysis module 50, fixture monitoring result acquisition module 60. DETAILED DESCRIPTION

[0012] The embodiments of the present application provide a fixture monitoring method for parts processing, which solves the technical problems that existing fixture monitoring methods usually only consider one or a few clamping methods, resulting in incomplete monitoring of workpiece processing conditions under different clamping methods, and limitations in data processing, resulting in poor monitoring accuracy and low intelligence.

[0013] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically introduced below in conjunction with the accompanying drawings of the specification. 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.

[0014] like Figure 1 As shown, an embodiment of the present application provides a fixture monitoring method for part processing, the method comprising: Determine the part clamping method and build a clamping database based on the clamping dynamics characteristics, wherein the part clamping method at least includes mechanical clamping, hydraulic clamping, electromagnetic clamping, and vacuum adsorption clamping.

[0015] Determine the part clamping method, which includes at least mechanical clamping, hydraulic clamping, electromagnetic clamping, and vacuum adsorption clamping. Among them, mechanical clamping is to use mechanical clamps, such as vises, chucks, etc., to clamp parts through mechanical force. This method is often used in processing occasions that require high precision and high stability; hydraulic clamping is to use the pressure generated by the hydraulic system to clamp parts through hydraulic clamps. This method is suitable for occasions that require large clamping force and fast operation; electromagnetic clamping is to use the magnetic force generated by electromagnets to clamp metal parts. This method is suitable for fast clamping and disassembly, and is not easy to damage the surface of the parts; vacuum adsorption clamping is to use negative pressure through vacuum suction cups to adsorb and clamp parts, which is usually used for thin plates or parts with smooth surfaces.

[0016] Dynamic characteristics describe the behavioral features of an object under force and motion, including force, vibration, etc. Through historical data, experiments or simulations, data such as clamping force, clamping stiffness, vibration characteristics, etc. under different clamping methods are collected, and the collected data are classified and stored in the database according to the clamping method. A clamping database is established to provide data support for fixture monitoring of part processing.

[0017] Furthermore, the construction of a clamping database based on clamping dynamics characteristics includes: Read historical clamping data, mine transmission characteristics and transmission relationships, the transmission relationship includes a power source transmission relationship and a power attenuation relationship; mine transmission constraint factors for the transmission characteristics, and determine the transmission constraint relationship; integrate the transmission characteristics, the transmission relationship and the transmission constraint relationship, and build the clamping database.

[0018] Extract historical clamping data from the recording system, including the clamping force, response time, friction loss, etc. of different types of clamps under various working conditions. Explore transmission characteristics, which are characteristics that describe the force transmission method and efficiency in the clamp system. Specifically, analyze each connection point in the clamp system to determine their role in the clamping process, for example, the transmission efficiency of the clamping force, that is, the force transmission efficiency from the power source, such as a hydraulic pump, to each part of the clamp; the clamping force response, that is, the response speed and stability of the clamp after the clamping force is applied; the characteristics of each connection point, that is, analyze the mechanical characteristics of each connection point in the clamp system, such as hinges, sliders, etc., including stiffness, friction coefficient, etc.

[0019] Excavate the transmission relationship. The transmission relationship includes the power source transmission relationship and the power attenuation relationship. The power source transmission relationship includes analyzing the force transmission path and efficiency from the power source, such as hydraulic pumps, motors, etc., to each part of the clamp, for example, the transmission efficiency of each component in the force transmission path from the hydraulic pump to the clamping claw; the power attenuation relationship includes analyzing the force attenuation caused by factors such as friction and deformation during the force transmission process, for example, the friction loss under different working conditions and its impact on the clamping force.

[0020] Identify transmission constraints, including mechanical constraints, environmental constraints, material property factors, power source property factors, etc., conduct data analysis on transmission constraints, and use historical data and experimental data to verify the impact of these factors on transmission characteristics, that is, measure the performance of the transmission system under different conditions through experiments, for example, by changing the temperature to measure the change in friction force, and verify the impact of ambient temperature on clamping force. Based on data analysis and experimental results, establish a transmission constraint relationship, which can describe the performance change of the transmission system under different constraint conditions.

[0021] The transmission characteristics, transmission relationships, and transmission constraint relationships are integrated to build a comprehensive clamping database, which can be used to optimize fixture design, improve the control accuracy of the clamping process, and provide reference in practical applications. For example, based on the data of transmission characteristics and constraint relationships, the performance of the fixture under different working conditions can be predicted to guide actual operations.

[0022] Based on the clamping database, a state memory unit is trained, wherein the state memory unit includes parallel state memory branches mapped to the part clamping mode.

[0023] The state memory unit is a model that can memorize and identify the state of the fixture. It can be understood as a neural network model with memory function. The state memory unit includes parallel state memory branches mapped to the part clamping method. The parallel state memory branches are independent state memory models built for each clamping method. These models work in parallel and process the data of the corresponding clamping methods respectively.

[0024] Extract the dynamic characteristic data under different clamping modes from the clamping database, extract the features of the data, and form a feature vector suitable for the training model. Use the processed data to train each parallel state memory branch. During the training process, supervised learning methods can be used to guide model learning through label data, such as normal state and abnormal state. Use the verification data set to verify the trained model and evaluate its performance, including indicators such as accuracy. Adjust the model parameters according to the verification results to optimize the model performance. Through the above steps, an efficient state memory unit is trained, which can monitor and analyze the fixture status in real time under different clamping modes, providing reliable support for the part processing process.

[0025] The fixture monitoring data of the target part is read, and the point cloud distribution data is preprocessed and screened, wherein the point cloud distribution data is based on the center of gravity of the part, and the multi-level preset supplementary step length and key points are used as distribution screening criteria.

[0026] Obtain real-time monitoring data of the target part in the fixture from sensors, monitoring equipment, etc. These data include information such as clamping force, position, vibration, etc., and obtain fixture monitoring data. Preprocess the fixture monitoring data, including data cleaning, that is, removing noise, outliers and invalid data to ensure data quality, and standardizing the data so that it is within the same dimension range for subsequent analysis.

[0027] Point cloud distribution data is screened. Specifically, the center of gravity of the part is calculated as the reference point of the point cloud distribution, recorded as the first point cloud, and key locations on the part, for example, special structural locations, such as inflection points, are determined as the second point cloud distribution. Based on multi-level preset step sizes, the first step size level is randomly determined, and the first point cloud and the second point cloud distribution are used as initial points to expand the point cloud. The preset step size is used for iterative expansion to gradually expand the range of the point cloud distribution until the coverage requirements are met. In each expansion iteration, point cloud data that meets the preset standards is screened out, and the point cloud data after multi-level step size expansion and screening is integrated to form the final point cloud distribution data.

[0028] Furthermore, the point cloud distribution data screening includes: Determine the center of gravity of the part as the first point cloud; determine the key site position of the part clamping as the second point cloud distribution; based on the multi-level preset step size, randomly determine the first step size level, take the first point cloud and the second point cloud distribution as the initial point, expand the point cloud based on the first step size level, iterate the point cloud expansion until the coverage requirement is met, integrate the point cloud distribution to determine the monitoring point cloud distribution; based on the monitoring point cloud distribution, screen the pre-processed fixture monitoring data.

[0029] Determine the center of gravity of the part, for example, obtain a three-dimensional model of the target part through a CAD model, perform mass distribution analysis on the three-dimensional model, calculate the mass of each part, calculate the center of gravity of the part according to the mass distribution, and use the coordinates of the center of gravity of the part as the first point cloud.

[0030] Determine the positions of key points for part clamping. Specifically, analyze the structure of the part, determine the possible clamping positions and force transmission paths, identify key points on the part, which are special structural positions, including inflection points, mutation points, hole edges, etc. Mark the identified key points on the 3D model and record their coordinates as the second point cloud distribution.

[0031] Define different levels of step sizes to control the expansion range of point cloud data. For example, three levels of step sizes can be preset, including small step size, medium step size, and large step size, corresponding to different expansion ranges, to determine the multi-level preset step sizes. Randomly select one from the preset step size levels as the initial step size level, that is, the first step size level.

[0032] The center of gravity (first point cloud) and key points (second point cloud distribution) of the part are used as the initial points, and the point cloud is expanded based on the selected step level. Specifically, the first point cloud and the second point cloud distribution are used as the initial point cloud set. For each point in the initial point cloud set, expansion is performed according to the current step level to generate a new point cloud. The newly generated point cloud is added to the point cloud set, and the expansion process is repeated until the point cloud coverage meets the requirements. The coverage requirement is a preset coverage standard, for example, covering more than 95% of the surface of the part. After each iterative expansion, the coverage of the current point cloud set is calculated. If the coverage does not meet the requirements, continue to expand; otherwise, stop expanding. After meeting the coverage requirements, the point cloud data is integrated to determine the monitoring point cloud distribution.

[0033] For the preprocessed fixture monitoring data, only the monitoring data corresponding to the monitoring point cloud distribution is retained, and other data are ignored.

[0034] In combination with the target clamping mode, the target memory branch based on the state memory unit is matched, the dynamic characteristics of the point cloud distribution data are analyzed, and the first monitoring result is determined.

[0035] According to the target clamping method of the determined target part, the memory branch that matches it is selected as the target memory branch to ensure the pertinence of the analysis. The preprocessed and screened point cloud distribution data is input into the selected target memory branch, and the target memory branch is used to analyze the dynamic characteristics of the point cloud data to predict and evaluate the dynamic response of the part during the clamping process. The analysis process includes vibration analysis, that is, identifying the vibration frequency and resonance point that may be generated by the part during the processing process, and evaluating its impact on the processing quality; stress-strain analysis, that is, evaluating the stress and strain of the part during the clamping and processing process to determine whether it is within the safe range; clamping force distribution analysis, that is, analyzing the distribution of the clamping force on the part to ensure uniform and stable clamping.

[0036] Based on the results of the dynamic characteristics analysis, the first monitoring result is determined. This result includes the evaluation of the part clamping state and the identification of potential problems. For example, if the analysis results show that the part is in a normal state under the current hydraulic clamping and processing conditions and all dynamic characteristic indicators are within the safe range, then the first monitoring result is normal; if the analysis results show that the dynamic characteristics exceed the safe range, then the first monitoring result is abnormal and corresponding measures need to be taken.

[0037] Furthermore, after the point cloud distribution data is subjected to dynamic characteristic analysis, the following steps are included: Determine N point cloud monitoring results based on the point cloud distribution data; perform a single point cloud power transmission analysis based on the clamping power connection point on the N point cloud monitoring results to determine the single point monitoring characteristics; perform a point cloud balance analysis on the N point cloud monitoring results to determine the global monitoring characteristics; determine the first monitoring result based on the single point monitoring characteristics and the global monitoring characteristics.

[0038] From the distribution of monitoring point cloud, select N key monitoring points, N is determined according to the actual key position, these monitoring points include the center of gravity, clamping point, inflection point and other positions of the part. Read the monitoring data corresponding to each monitoring point, organize the data of each monitoring point into a monitoring result, and form N point cloud monitoring results. Each monitoring result includes multiple monitoring parameters, such as vibration frequency, clamping force value, etc.

[0039] Determine the clamping power connection point, that is, the intermediate structural point between the power source, such as hydraulic pressure, pneumatic pressure, and the fixture. For each monitoring point, perform power conduction analysis, such as establishing a power conduction model, simulating the process of the power source being transmitted to the fixture through the intermediate structural point, and then to the workpiece through the model, and analyzing the degree of power attenuation during the conduction process during the simulation. For example, according to the power conduction model, calculate the power attenuation value of each monitoring point, and determine the single-point monitoring characteristics of each monitoring point based on the results of the power conduction analysis, including power transmission efficiency, clamping force response, power attenuation, etc.

[0040] Point cloud balance analysis includes checking the spatial distribution balance and numerical balance of monitoring point cloud data to ensure that the monitoring data is evenly distributed on the entire part and that there is no obvious deviation in the data of each monitoring point. Specifically, analyze the spatial distribution of each monitoring point on the part to ensure that the monitoring points cover the key areas of the entire part. For example, calculate the distance between each monitoring point to check whether there is too dense or too sparse point cloud distribution; analyze the data value of each monitoring point to check whether there are significant anomalies or deviations. For example, use statistical methods such as mean, variance, and standard deviation to measure the data balance of each monitoring point. Combine the analysis results of spatial distribution balance and numerical balance to determine the global monitoring characteristics of the part.

[0041] The single-point monitoring characteristics are integrated with the global monitoring characteristics to form a comprehensive first monitoring result.

[0042] Read the part processing task and determine the eccentricity tolerance range, perform working condition eccentricity analysis based on spatial position and fixture limit, and determine the second monitoring result, wherein the working condition eccentricity includes the part clamping eccentricity and the relative eccentricity between the tool clamping part and the part clamping part.

[0043] The processing task information of the current part is read from the processing task system, including the processing path, processing speed, required tools, etc. According to the processing task and the geometric characteristics of the part, the allowable eccentricity range, that is, the eccentricity tolerance interval, is determined. This interval defines the degree of eccentricity that the part can tolerate during the processing to ensure the processing accuracy and quality. The eccentricity tolerance interval includes the orientation tolerance interval, that is, the eccentricity angle allowed in each direction, for example, set to ±2 degrees, and the distance tolerance interval, that is, the eccentricity distance allowed in each direction, for example, set to ±0.5 mm.

[0044] Perform working condition eccentricity analysis, specifically, perform part clamping eccentricity analysis to analyze whether there is eccentricity in the clamping position of the part in the fixture, that is, whether the center of gravity of the part is consistent with the clamping center. If there is eccentricity, calculate the eccentricity distance and eccentricity direction; perform relative eccentricity analysis based on the tool clamping part and the part clamping part, analyze the relative position relationship between the processing tool and the part, and determine the relative eccentricity between the tool clamping part and the part clamping part. Relative eccentricity may cause processing errors and clamping instability.

[0045] The second monitoring result is determined by comprehensively analyzing the eccentricity of part clamping and the relative eccentricity between tool and part. For example, if the eccentricity is within the allowable tolerance range and does not affect the processing quality, the second monitoring result is normal. If the eccentricity exceeds the eccentricity tolerance range, it may cause processing errors or unstable clamping and requires immediate adjustment, then the second monitoring result is abnormal.

[0046] Furthermore, the working condition eccentricity includes part clamping eccentricity, including: The geometric structure of the target part is read to determine the center of the arc; based on the center of the arc, the target part is subjected to arc center eccentricity calibration to determine the first eccentric spatial distance, wherein the eccentricity calibration is performed based on the relative spatial distance between the processed arc center and the actual arc center; based on the relative clamping position of the clamp and the target part, a clamp limit deviation analysis is performed to determine the second deviation limit area; based on the first eccentric spatial distance and the second deviation limit area, the clamping eccentricity result is determined and added to the second monitoring result.

[0047] Read the geometric structure information of the target part from the CAD file or other geometric data source, identify the arc structure of the target part, including the starting point, end point and radius of the arc, calculate the center coordinates of the arc according to the starting point and end point of the arc, usually the center coordinates of the circle, and determine the center of the arc.

[0048] Use measurement tools or analysis software to detect the actual arc center of the target part, which may deviate from the ideal center due to processing errors or design problems. Take the arc center as the reference point and calculate the relative spatial distance between the processed arc center and the actual arc center. This distance is the first eccentric spatial distance, and the eccentric distance can be expressed as Euclidean distance.

[0049] Analyze the relative clamping position relationship between the fixture and the target part, including the fixture's fixed point and the target part's key support point. Based on the relative clamping position, analyze the possible deviation of the fixture under the limit condition. For example, combine engineering knowledge with actual conditions to analyze, consider the fixture's structural characteristics, working environment and use conditions, use computer-aided engineering software to perform fixture deviation analysis, determine the possible deviation range of the fixture under different working conditions, and determine the second deviation limit area of ​​the fixture under the limit condition based on the deviation analysis results.

[0050] Combined with the first eccentric space distance and the second deviation limit area, the possible eccentricity of the fixture in actual work is calculated. Computer-aided engineering software is also used to determine the clamping eccentricity result, which is a quantitative value indicating the degree of clamping eccentricity. The clamping eccentricity result is integrated into the second monitoring result.

[0051] Further, the working condition eccentricity includes the relative eccentricity based on the tool clamping part and the part clamping part, including: The part processing task is read to determine the relative clamping position of the entire processing cycle, wherein the relative clamping position is marked with a processing node; the relative tolerance interval of the eccentricity tolerance interval is identified, wherein the relative tolerance interval includes an orientation tolerance interval and a distance tolerance interval; based on the relative tolerance interval, the relative off-axis calibration is performed on the relative clamping position to determine the relative eccentricity result.

[0052] The processing task information of the current part is read from the processing task system. According to the processing node and fixture design, the relative clamping position of the fixture and the part at each processing node is calculated, and the relative clamping position of each processing node is marked for subsequent eccentricity tolerance interval identification.

[0053] The eccentricity tolerance range refers to the range of relative eccentricity between the fixture and the part allowed during the processing, including the orientation tolerance range and the distance tolerance range. The orientation tolerance range is determined based on the fixture design and processing tasks. The orientation tolerance range can be an angle range or a direction mark, indicating the rotational deviation allowed by the fixture during the processing; the distance tolerance range is determined based on the fixture design and processing tasks. The distance tolerance range can be a linear distance or a gap mark, indicating the linear deviation or gap allowed by the fixture during the processing. The relative clamping position of the fixture and the part at each processing node is identified and marked with a tolerance range, and the relative tolerance range at each processing node is determined based on the orientation tolerance range and the distance tolerance range.

[0054] Relative off-axis calibration is a method used to determine the relative eccentricity result. The basic idea is to compare the relative clamping position with the relative tolerance interval to determine the eccentricity between the fixture and the part. Specifically, from the relative clamping position of the entire machining cycle, select the specific machining nodes that need to be calibrated for relative off-axis calibration, and determine the corresponding tolerance interval range based on the relative tolerance interval. Compare and analyze the relative clamping position with the relative tolerance interval to determine the relative eccentricity result. If the relative clamping position is within the relative tolerance interval, it is judged to meet the tolerance requirements and the relative eccentricity result is normal; if the relative clamping position exceeds the relative tolerance interval, it is judged to not meet the tolerance requirements and requires further processing.

[0055] The first monitoring result and the second monitoring result are used as the fixture monitoring result of the target part.

[0056] Integrate the first monitoring result with the second monitoring result, conduct a comprehensive analysis, and consider the mutual influence of various indicators. For example, although the clamping force is evenly distributed, if the eccentricity is large, it may still lead to stress concentration during processing, which requires further verification. In this way, a complete monitoring result of the target part fixture is formed to provide comprehensive guidance for the part processing process.

[0057] Further, after determining the fixture monitoring result of the target part, it includes: Based on the fixture monitoring results, clamping control factors are determined; based on the clamping control factors, multi-factor control optimization analysis is performed with factor control collision as a constraint to determine a composite control scheme; based on the composite control scheme, fixture clamping feedback control based on the target part is performed.

[0058] Analyze the monitoring results of the fixture, including monitoring data such as clamping eccentricity, fixture limit deviation, and clamping force. According to the monitoring results, determine the key control factors that affect the clamping performance of the fixture, such as clamping force adjustment, fixture structure adjustment, fixture position adjustment, etc., prioritize the determined clamping control factors, and determine the priority based on the degree of impact on the clamping performance and the difficulty of control.

[0059] The clamping control factors are used as control parameters to avoid fixture collision and conflict problems during the processing process. Multi-factor control optimization algorithms, such as genetic algorithms and simulated annealing algorithms, are used to combine and optimize the fixture control factors. The mutual influence and trade-offs between different factors are considered to seek the optimal clamping control scheme. According to the results of the optimization analysis, a composite control scheme is determined, including a combined control scheme of multiple factors such as clamping force adjustment, fixture structure adjustment, and fixture position adjustment.

[0060] The determined composite control scheme is applied to the actual fixture clamping operation, and the fixture clamping feedback control is performed according to the specific processing process and process requirements of the target parts. That is, the effect of the control scheme after implementation is evaluated, including changes in indicators such as clamping stability, processing accuracy, and efficiency. According to the feedback results and actual conditions, the composite control scheme is adjusted in time to ensure the stability and optimization of the fixture clamping performance, thereby improving processing efficiency and product quality.

[0061] In summary, the fixture monitoring method for parts processing provided by the embodiment of the present application has the following technical effects: 1. By integrating various clamping methods such as mechanical clamping, hydraulic clamping, electromagnetic clamping, vacuum adsorption clamping, etc., the application scope and monitoring accuracy of the monitoring system are improved; 2. Through the training state memory unit, the training state memory unit includes parallel state memory branches mapped to different clamping modes, which realizes the effective recognition and matching of different clamping states and improves the intelligence level of the monitoring system; 3. Through point cloud distribution data screening and dynamic characteristics analysis, accurate monitoring and analysis of workpiece clamping conditions are achieved, providing a reliable basis for subsequent regulation and optimization; 4. Through the eccentricity analysis of working conditions and the regulation based on the limit of the fixture, the effective monitoring and regulation of the part clamping eccentricity and the relative eccentricity between the tool clamping part and the part clamping part are realized, thereby improving the processing accuracy and stability.

[0062] In summary, the fixture monitoring method for parts processing effectively solves the limitations of existing fixture monitoring methods by integrating multiple clamping methods, applying state memory units, point cloud data screening and dynamic characteristics analysis, as well as working condition eccentricity analysis and fixture control, and improves the intelligence, accuracy and stability of the fixture monitoring system.

[0063] Based on the same inventive concept as the fixture monitoring method for parts processing in the aforementioned embodiment, Figure 2 As shown, an embodiment of the present application provides a fixture monitoring system for part processing, the system comprising: A clamping database building module 10, wherein the clamping database building module 10 is used to determine a part clamping method and build a clamping database based on clamping dynamic characteristics, wherein the part clamping method at least includes mechanical clamping, hydraulic clamping, electromagnetic clamping, and vacuum adsorption clamping; A state memory unit training module 20, the state memory unit training module 20 is used to train a state memory unit based on the clamping database, the state memory unit comprising a parallel state memory branch mapped to the part clamping mode; A point cloud distribution data screening module 30, which is used to read the fixture monitoring data of the target part, pre-process and screen the point cloud distribution data, wherein the point cloud distribution data is based on the center of gravity of the part, and multi-level preset supplementary step lengths and key points are used as distribution screening criteria; A dynamic characteristic analysis module 40, the dynamic characteristic analysis module 40 is used to combine the target clamping mode, match the target memory branch based on the state memory unit, perform dynamic characteristic analysis on the point cloud distribution data, and determine a first monitoring result; A working condition eccentricity analysis module 50, which is used to read the part processing task and determine the eccentricity tolerance range, perform working condition eccentricity analysis based on the spatial position and the fixture limit, and determine the second monitoring result, wherein the working condition eccentricity includes the part clamping eccentricity and the relative eccentricity between the tool clamping part and the part clamping part; A fixture monitoring result acquisition module 60 is used to obtain the fixture monitoring result of the target part based on the first monitoring result and the second monitoring result.

[0064] Furthermore, the system further comprises a clamping database building module to perform the following operation steps: Read historical clamping data to mine transmission characteristics and transmission relationships, including power source transmission relationship and power attenuation relationship; Mining transmission constraint factors of the transmission characteristics and determining transmission constraint relationships; The transmission characteristics, the transmission relationship and the transmission constraint relationship are integrated to build the clamping database.

[0065] Furthermore, the system further includes a fixture monitoring data screening module to perform the following operation steps: Determine the center of gravity of the part as the first point cloud; Determine the key position of the part clamping as the second point cloud distribution; Based on the multi-level preset step size, a first step size level is randomly determined, the first point cloud and the second point cloud distribution are used as initial points, point cloud expansion is performed based on the first step size level, and point cloud expansion is performed iteratively until the coverage requirement is met, and point cloud distribution integration is performed to determine the monitoring point cloud distribution; Based on the monitoring point cloud distribution, the pre-processed fixture monitoring data is screened.

[0066] Furthermore, the system further includes a first monitoring result determination module to perform the following operation steps: Determine N point cloud monitoring results based on the point cloud distribution data; Performing a single point cloud power transmission analysis based on a clamping power connection point on the N point cloud monitoring results to determine a single point monitoring characteristic; Performing point cloud balance analysis on the N point cloud monitoring results to determine global monitoring characteristics; Based on the single-point monitoring characteristic and the global monitoring characteristic, the first monitoring result is determined.

[0067] Furthermore, the system further includes a second monitoring result acquisition module to perform the following operation steps: Reading the geometric structure of the target part and determining the center of the arc; Taking the arc center as a reference, the target part is subjected to arc center eccentricity calibration to determine a first eccentricity spatial distance, wherein the eccentricity calibration is performed based on the relative spatial distance between the machining arc center and the actual arc center; Based on the relative clamping position between the fixture and the target part, a fixture limit deviation analysis is performed to determine a second deviation limit area; Based on the first eccentric spatial distance and the second deviation limit area, a clamping eccentricity result is determined and added to the second monitoring result.

[0068] Furthermore, the system further comprises a relative eccentricity result determination module to perform the following operation steps: Reading the part processing task, determining the relative clamping position of the entire processing cycle, wherein the relative clamping position is marked with a processing node; Identifying a relative tolerance interval of the eccentricity tolerance interval, wherein the relative tolerance interval includes an orientation tolerance interval and a distance tolerance interval; Based on the relative tolerance range, a relative off-axis calibration is performed on the relative clamping position to determine a relative eccentricity result.

[0069] Furthermore, the system also includes a clamping feedback control module to perform the following operation steps: Determining clamping control factors based on the clamp monitoring results; Based on the clamping control elements, taking element control collision as a constraint, a multi-element control optimization analysis is performed to determine a composite control scheme; Based on the composite control scheme, clamping feedback control of the target part is performed.

[0070] Through the aforementioned detailed description of the fixture monitoring method for parts processing in this specification, those skilled in the art can clearly understand the fixture monitoring system for parts processing in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0071] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus, wherein the processor of the computer device is used to provide computing and control capabilities; the memory of the computer device includes a non-volatile storage medium and an internal memory, wherein the non-volatile storage medium stores an operating system, a computer program and a database, and the internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium; the network interface of the computer device is used to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement a fixture monitoring method for part processing.

[0072] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0073] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0074] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A fixture monitoring method for parts processing, characterized in that: The method comprises: Determine the part clamping method and build a clamping database based on the clamping dynamics characteristics, wherein the part clamping method at least includes mechanical clamping, hydraulic clamping, electromagnetic clamping, and vacuum adsorption clamping; Based on the clamping database, training a state memory unit, the state memory unit comprising a parallel state memory branch mapped to the part clamping mode; Read the fixture monitoring data of the target part, pre-process and screen the point cloud distribution data, wherein the point cloud distribution data is based on the center of gravity of the part, and the multi-level preset step length and key points are used as distribution screening criteria; In combination with the target clamping mode, the target memory branch based on the state memory unit is matched, and the dynamic characteristic analysis of the point cloud distribution data is performed to determine the first monitoring result; Read the part processing task and determine the eccentricity tolerance range, perform the working condition eccentricity analysis based on the spatial position and the fixture limit, and determine the second monitoring result, wherein the working condition eccentricity includes the part clamping eccentricity and the relative eccentricity between the tool clamping part and the part clamping part; The first monitoring result and the second monitoring result are used as the fixture monitoring result of the target part.

2. The method according to claim 1, characterized in that The construction of a clamping database based on clamping dynamics characteristics includes: Read historical clamping data to mine transmission characteristics and transmission relationships, including power source transmission relationship and power attenuation relationship; Mining transmission constraint factors of the transmission characteristics and determining transmission constraint relationships; The transmission characteristics, the transmission relationship and the transmission constraint relationship are integrated to build the clamping database.

3. The method according to claim 1, characterized in that The point cloud distribution data screening includes: Determine the center of gravity of the part as the first point cloud; Determine the key position of the part clamping as the second point cloud distribution; Based on the multi-level preset step size, a first step size level is randomly determined, the first point cloud and the second point cloud distribution are used as initial points, point cloud expansion is performed based on the first step size level, and point cloud expansion is performed iteratively until the coverage requirement is met, and point cloud distribution integration is performed to determine the monitoring point cloud distribution; Based on the monitoring point cloud distribution, the pre-processed fixture monitoring data is screened.

4. The method according to claim 1, characterized in that After the point cloud distribution data is subjected to dynamic characteristic analysis, the following steps are included: Determine N point cloud monitoring results based on the point cloud distribution data; Performing a single point cloud power transmission analysis based on a clamping power connection point on the N point cloud monitoring results to determine a single point monitoring characteristic; Performing point cloud balance analysis on the N point cloud monitoring results to determine global monitoring characteristics; Based on the single-point monitoring characteristic and the global monitoring characteristic, the first monitoring result is determined.

5. The method according to claim 1, characterized in that The working condition eccentricity includes part clamping eccentricity, including: Reading the geometric structure of the target part and determining the center of the arc; Taking the arc center as a reference, the target part is subjected to arc center eccentricity calibration to determine a first eccentricity spatial distance, wherein the eccentricity calibration is performed based on the relative spatial distance between the machining arc center and the actual arc center; Based on the relative clamping position between the fixture and the target part, a fixture limit deviation analysis is performed to determine a second deviation limit area; Based on the first eccentric spatial distance and the second deviation limit area, a clamping eccentricity result is determined and added to the second monitoring result.

6. The method according to claim 1, characterized in that The working condition eccentricity includes the relative eccentricity between the tool holder and the part holder, including: Reading the part processing task, determining the relative clamping position of the entire processing cycle, wherein the relative clamping position is marked with a processing node; Identifying a relative tolerance interval of the eccentricity tolerance interval, wherein the relative tolerance interval includes an orientation tolerance interval and a distance tolerance interval; Based on the relative tolerance range, a relative off-axis calibration is performed on the relative clamping position to determine a relative eccentricity result.

7. The method according to claim 1, characterized in that After determining the fixture monitoring result of the target part, it includes: Determining clamping control factors based on the clamp monitoring results; Based on the clamping control elements, taking element control collision as a constraint, a multi-element control optimization analysis is performed to determine a composite control scheme; Based on the composite control scheme, clamping feedback control of the target part is performed.

8. A fixture monitoring system for parts processing, characterized in that: A system for implementing a fixture monitoring method for part processing according to any one of claims 1 to 7, the system comprising: A clamping database building module, wherein the clamping database building module is used to determine a part clamping method and build a clamping database based on clamping dynamic characteristics, wherein the part clamping method includes at least mechanical clamping, hydraulic clamping, electromagnetic clamping, and vacuum adsorption clamping; A state memory unit training module, the state memory unit training module is used to train a state memory unit based on the clamping database, the state memory unit includes a parallel state memory branch mapped to the part clamping mode; A point cloud distribution data screening module, which is used to read the fixture monitoring data of the target part, pre-process and screen the point cloud distribution data, wherein the point cloud distribution data is based on the center of gravity of the part, and multi-level preset supplementary step lengths and key points are used as distribution screening criteria; A dynamic characteristic analysis module, the dynamic characteristic analysis module is used to combine the target clamping mode, match the target memory branch based on the state memory unit, perform dynamic characteristic analysis on the point cloud distribution data, and determine a first monitoring result; A working condition eccentricity analysis module, which is used to read the part processing task and determine the eccentricity tolerance range, perform working condition eccentricity analysis based on the spatial position and the fixture limit, and determine the second monitoring result, wherein the working condition eccentricity includes the part clamping eccentricity and the relative eccentricity between the tool clamping part and the part clamping part; A fixture monitoring result acquisition module is used to obtain the fixture monitoring result of the target part based on the first monitoring result and the second monitoring result.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the fixture monitoring method for part processing 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 fixture monitoring method for part processing according to any one of claims 1 to 7 are implemented.

Images