CN117047569A - Tool clamp polishing method and device based on sensor data interaction - Google Patents
Tool clamp polishing method and device based on sensor data interaction Download PDFInfo
- Publication number
- CN117047569A CN117047569A CN202311238910.9A CN202311238910A CN117047569A CN 117047569 A CN117047569 A CN 117047569A CN 202311238910 A CN202311238910 A CN 202311238910A CN 117047569 A CN117047569 A CN 117047569A
- Authority
- CN
- China
- Prior art keywords
- polishing
- control
- data
- tool pliers
- parameters
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005498 polishing Methods 0.000 title claims abstract description 181
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000003993 interaction Effects 0.000 title claims abstract description 37
- 238000012216 screening Methods 0.000 claims abstract description 14
- 238000012795 verification Methods 0.000 claims description 31
- 239000011800 void material Substances 0.000 claims description 31
- 238000004458 analytical method Methods 0.000 claims description 21
- 238000009826 distribution Methods 0.000 claims description 21
- 230000003746 surface roughness Effects 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 11
- 239000000463 material Substances 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 18
- 238000009825 accumulation Methods 0.000 abstract description 5
- 238000012545 processing Methods 0.000 description 30
- 238000004422 calculation algorithm Methods 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 13
- 230000008569 process Effects 0.000 description 10
- 238000007517 polishing process Methods 0.000 description 7
- 238000003754 machining Methods 0.000 description 6
- 238000005259 measurement Methods 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 238000000227 grinding Methods 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000011960 computer-aided design Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 239000002173 cutting fluid Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B1/00—Processes of grinding or polishing; Use of auxiliary equipment in connection with such processes
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B41/00—Component parts such as frames, beds, carriages, headstocks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B49/00—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation
- B24B49/12—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation involving optical means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B51/00—Arrangements for automatic control of a series of individual steps in grinding a workpiece
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Constituent Portions Of Griding Lathes, Driving, Sensing And Control (AREA)
Abstract
The invention provides a tool clamp polishing method and device based on sensor data interaction, which relate to the technical field of tool clamp polishing and comprise the following steps: and executing basic data interaction of the tool pliers to construct a standard data set, executing three-dimensional data scanning on the blank to construct a three-dimensional fitting model, matching with a mark center point to determine a three-dimensional contour, generating polishing size data, reading equipment parameters to construct a control model, acquiring N control execution strategies, setting speed-quality balance data, carrying out strategy screening to obtain control parameters, executing polishing control of the tool pliers, executing node image acquisition of polishing, generating auxiliary control information, carrying out real-time adjustment, and completing polishing control of the tool pliers according to an adjustment result. The invention solves the technical problems that the traditional polishing method mainly depends on manual operation and experience accumulation, and the polishing parameters are difficult to adjust in a self-adaptive manner according to real-time requirements, so that the efficiency is low, errors are easy to occur, and the target polishing effect cannot be accurately and stably realized.
Description
Technical Field
The invention relates to the technical field of tool clamp polishing, in particular to a tool clamp polishing method and device based on sensor data interaction.
Background
The tool pliers polishing technology is a very important link in the field of machine manufacturing, relates to a plurality of aspects such as materialogy, machine manufacturing, lean production and the like, is promoted by industry demands and technological progress, and is continuously perfected and improved along with the time. However, the conventional tool pliers polishing method has a certain disadvantage, and a certain liftable space exists for tool pliers polishing.
Disclosure of Invention
The application provides a tool clamp polishing method and a tool clamp polishing device based on sensor data interaction, and aims to solve the technical problems that the traditional polishing method mainly depends on manual operation and experience accumulation, and polishing parameters are difficult to adjust in a self-adaptive manner according to real-time requirements, so that the efficiency is low, errors are prone to occur, and the target polishing effect cannot be accurately and stably achieved.
In view of the above problems, the application provides a tool clamp polishing method and device based on sensor data interaction.
In a first aspect of the disclosure, a method for grinding tool pliers based on sensor data interaction is provided, the method comprising: performing basic data interaction of the tool pliers, and constructing a standard data set of the tool pliers according to the basic data, wherein the standard data set comprises standard size constraint and surface roughness constraint; performing three-dimensional data scanning on a blank, constructing a three-dimensional fitting model according to a point cloud data set, matching an identification center point, determining a three-dimensional contour according to the three-dimensional fitting model and the identification center point, and generating polishing size data according to the three-dimensional contour and the standard data set; reading equipment parameters of polishing equipment, and constructing a control model according to the equipment parameters; inputting the polishing size data and the material data into the control model, and outputting N control execution strategies; setting speed-quality balance data, and performing strategy screening of the N control execution strategies based on the balance data to obtain control parameters; controlling the polishing equipment to execute polishing control of the tool pliers based on the control parameters, executing node image acquisition of polishing through an image acquisition device, and generating auxiliary control information according to an image acquisition result; and adjusting the control parameters in real time through the auxiliary control information, and finishing polishing control of the tool pliers according to the real-time adjustment result.
In another aspect of the present disclosure, a tool pliers polishing device based on sensor data interaction is provided, the device comprising: the data interaction module is used for performing basic data interaction of the tool pliers and constructing a standard data set of the tool pliers according to the basic data, wherein the standard data set comprises standard size constraint and surface roughness constraint; the data scanning module is used for executing three-dimensional data scanning on a blank, constructing a three-dimensional fitting model according to a point cloud data set, matching an identification center point, determining a three-dimensional contour according to the three-dimensional fitting model and the identification center point, and generating polishing size data according to the three-dimensional contour and the standard data set; the parameter reading module is used for reading equipment parameters of polishing equipment and constructing a control model according to the equipment parameters; the strategy output module is used for inputting the polishing size data and the material data into the control model and outputting N control execution strategies; the strategy screening module is used for setting speed-quality balance data, and carrying out strategy screening of the N control execution strategies based on the balance data to obtain control parameters; the auxiliary information generation module is used for controlling the polishing equipment to execute polishing control of the tool pliers based on the control parameters, executing node image acquisition of polishing through the image acquisition device and generating auxiliary control information according to an image acquisition result; and the polishing control module is used for adjusting the control parameters in real time through the auxiliary control information and finishing polishing control of the tool pliers according to the real-time adjustment result.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
performing basic data interaction of the tool pliers, constructing a standard data set, including standard size constraint and surface roughness constraint, performing three-dimensional data scanning on blanks, constructing a three-dimensional fitting model, matching an identification center point, determining a three-dimensional contour, generating polishing size data, reading equipment parameters, constructing a control model, inputting the control model, outputting N control execution strategies, setting speed-quality balance data, performing strategy screening to obtain control parameters, controlling polishing equipment to perform polishing control of the tool pliers, performing polishing node image acquisition, generating auxiliary control information, performing real-time adjustment on the control parameters, and completing polishing control of the tool pliers according to real-time adjustment results. The method solves the technical problems that the traditional polishing method mainly depends on manual operation and experience accumulation, has the defects of low efficiency and easy error due to difficulty in adaptively adjusting polishing parameters according to real-time requirements, and cannot accurately and stably realize the target polishing effect, realizes the accurate control of the polishing process by utilizing sensor data interaction and real-time control, and carries out self-adaptive adjustment on the polishing parameters, thereby greatly improving the stability and consistency of the polishing effect and achieving the technical effects of improving the flexibility and the intelligent degree of machining.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
FIG. 1 is a schematic flow chart of a tool clamp polishing method based on sensor data interaction according to an embodiment of the application;
FIG. 2 is a schematic flow chart of a possible process for generating a real-time adjustment result in a tool pliers polishing method based on sensor data interaction according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a possible process for performing polishing control of a subsequent tool holder in a tool holder polishing method based on sensor data interaction according to an embodiment of the present application;
fig. 4 is a schematic diagram of a possible structure of a tool pliers polishing device based on sensor data interaction according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a data interaction module 10, a data scanning module 20, a parameter reading module 30, a strategy output module 40, a strategy screening module 50, an auxiliary information generating module 60 and a polishing control module 70.
Detailed Description
The embodiment of the application solves the technical problems that the traditional polishing method mainly depends on manual operation and experience accumulation, is difficult to adaptively adjust polishing parameters according to real-time requirements, has low efficiency and is easy to make mistakes, so that a target polishing effect cannot be accurately and stably realized, realizes the accurate control of a polishing process by utilizing sensor data interaction and real-time control, and adaptively adjusts the polishing parameters, thereby greatly improving the stability and consistency of the polishing effect and achieving the technical effects of improving the flexibility and the intelligent degree of machining.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Example 1
As shown in fig. 1, an embodiment of the present application provides a tool pliers polishing method based on sensor data interaction, the method including:
step S100: performing basic data interaction of the tool pliers, and constructing a standard data set of the tool pliers according to the basic data, wherein the standard data set comprises standard size constraint and surface roughness constraint;
specifically, basic data related to the tool pliers, such as three-dimensional shapes, positions, process materials and the like, are collected through the sensors, standard size constraints and surface roughness constraints of the tool pliers are designed and defined according to the basic data, specifically, the elements such as the sizes, the curvatures and the like of all parts are determined through size measurement, detection and analysis of the mathematical model, the surface roughness characteristics are extracted, corresponding constraint conditions including the standard size constraint conditions and the surface roughness constraint conditions are set, so that a complete set of standard data sets is formed, and good data support is provided for integration of follow-up polishing control.
Step S200: performing three-dimensional data scanning on a blank, constructing a three-dimensional fitting model according to a point cloud data set, matching an identification center point, determining a three-dimensional contour according to the three-dimensional fitting model and the identification center point, and generating polishing size data according to the three-dimensional contour and the standard data set;
specifically, the blank is subjected to three-dimensional measurement by using technologies such as laser measurement and computer vision, data such as shape, geometric structure and surface characteristics are acquired and converted into a point cloud data set, the point cloud data set is processed by adopting a surface fitting method, a three-dimensional fitting model capable of representing the accurate shape of the whole blank is generated, and a center point is identified. The three-dimensional model and the identified center point are used to calculate and generate the outline of the blank to further control the edge and angle of the sanding. And calculating or abstracting the profile and physical quantity of the surface characteristics of the workpiece according to the determined three-dimensional profile and the standard data set, and generating polishing size data for subsequent processing control.
Step S300: reading equipment parameters of polishing equipment, and constructing a control model according to the equipment parameters;
specifically, the polishing equipment is connected, real-time monitoring and learning are carried out on the polishing equipment through equipment such as a sensor and an encoder, real-time displacement, rotation angle, load and other parameter data are collected and converted into digital signals, a mathematical model is built according to the equipment parameters by combining CAD (computer aided design or manufacturing) technology, so that motion simulation is carried out, the motion track and the processing speed of the equipment are predicted and adjusted, and further accurate control is realized.
Step S400: inputting the polishing size data and the material data into the control model, and outputting N control execution strategies;
specifically, the obtained polishing size data and material data are input into a control model to form three-dimensional space and feature description of a workpiece, the control model constructed according to the input data is utilized to operate, algorithms in the computer science fields such as AI, machine learning, deep neural network and the like are adopted to process and optimize the input data in the control model, N strategies are designed and generated, N is the number of the generated strategies, for example, 5 generated strategies, such as various processing schemes such as edge deburring, surface polishing and the like.
Step S500: setting speed-quality balance data, and performing strategy screening of the N control execution strategies based on the balance data to obtain control parameters;
specifically, according to the designed machine and workpiece characteristics, the machining capacity of the equipment and the realization target are analyzed, the target data of speed-quality balance is determined, a kinematic model of the workpiece and the equipment is established based on the set target, control parameters are calculated, corresponding speed and rotating speed are found based on the target balance value, further, the strategy which does not accord with the balance data is reduced by screening the N control execution strategies aiming at the rotating speed, the stepping distance and the like, and according to the control model, the optimal polishing tool, the operation method and the motion track are selected to obtain the optimal quality and the optimal efficiency, and the optimal strategy set is obtained. For the strategies, the control parameters are monitored and updated in real time by utilizing a field monitoring technology and a real-time data processing means, the processing parameters are dynamically adjusted by combining factors such as response time and measurement precision of equipment, and the optimal control parameters and control instructions are output so as to achieve the optimal effect at the moment.
Step S600: controlling the polishing equipment to execute polishing control of the tool pliers based on the control parameters, executing node image acquisition of polishing through an image acquisition device, and generating auxiliary control information according to an image acquisition result;
specifically, corresponding control instructions are generated according to the obtained control parameters and are input into a control system of polishing equipment, tool pliers in the polishing equipment are controlled by the control system to carry out polishing control operation, polishing tasks are executed according to a plan, and feedback information is recorded. The nodes of the polished workpiece are acquired in real time through an image acquisition device such as a camera, the acquired image data are transmitted to an image processing system, the acquired image is analyzed and processed through an image processing algorithm, such as filtering, segmentation, feature extraction and other operations are performed on the acquired image, point clouds are generated, polishing points are corrected according to motion state analysis and change, and auxiliary control information such as pattern matching, contour measurement and the like is generated so as to optimize and monitor the polishing process.
Step S700: and adjusting the control parameters in real time through the auxiliary control information, and finishing polishing control of the tool pliers according to the real-time adjustment result.
Specifically, the auxiliary control information is analyzed and processed to obtain a plurality of effective real-time adjustment information, such as tool position, processing speed, strength and the like, algorithms of machine learning, deep neural network and the like are adopted, the real-time adjustment information is combined with historical data, based on self-learning of a system, the characteristics of equipment and proper parameters of the polishing effect are gradually known, various parameter values are generated according to different requirements of a polishing task, and the optimal control parameters are provided for the current polishing task. And the control system is utilized to realize real-time control of the tool pliers according to the real-time adjustment information and the self-adaptive learning result, and finish the polishing task according to the preset polishing path.
Further, as shown in fig. 2, step S700 of the present application further includes:
step S710: performing control fitting based on the control parameters, and setting calibration control results of M nodes, wherein M is a positive integer greater than 2;
step S720: after polishing control of any node is completed, the image acquisition device is used for acquiring depth images of the tool pliers, and depth image data of the tool pliers nodes are constructed;
step S730: and performing polishing control verification according to the calibration control result and the depth image data, and generating the real-time adjustment result based on the polishing control verification result.
Specifically, according to the obtained control parameters, data analysis and digital model establishment are performed, original control data are fitted into a curve which meets control requirements by using curve fitting technology, for example, a polynomial curve fitting algorithm, the generated curve is discretized at equal intervals of M points, wherein M is a positive integer which is larger than 2, the number of nodes is represented, for example, the discretization is performed at equal intervals of 10 points, 10 nodes are obtained, the discretized nodes are calibrated and optimized by using algorithms such as fuzzy control and PID control, and M calibration control results are obtained through training and debugging, so that M calibration control results are obtained.
The tool pliers of each node in the grinding process are subjected to depth image acquisition by technical means such as a lens and laser, acquired data are transmitted to an image processing system, and based on the acquired data, the depth image is further analyzed and processed by utilizing a digital image processing algorithm, such as brightness calibration, color space conversion, denoising and the like, so that high-precision depth image data are obtained.
According to the calibration control result and the depth image data, polishing control is executed, feedback information is recorded, whether the control effect meets the requirement is verified, the recorded data and information in the actual polishing process are analyzed and processed to obtain various indexes of the current polishing task, such as precision, speed, workpiece surface quality and the like, and according to the obtained analysis result, a real-time adjustment result, such as control parameter values, polishing path planning and the like, is generated by combining an intelligent algorithm and a self-adaptive learning technology, so that basis is provided for optimization of the follow-up polishing task.
Further, step S710 of the present application further includes:
step S711: acquiring acquisition coordinates and acquisition control data of the image acquisition device;
step S712: extracting point cloud data of the node tool pliers according to the acquisition coordinates, the acquisition control data and the depth image data, and constructing a node size verification data set;
step S713: performing image feature analysis on the depth image data, generating a rough feature recognition result, and constructing a surface state verification data set;
step S714: and carrying out control verification of the calibration control result through the node size verification data set and the surface state verification data set.
Specifically, the image acquisition device is accurately positioned to a polishing processing area by using a sensor, an acquisition visual angle and an acquisition range of the image acquisition device are determined, a coordinate system is established in the acquisition device by methods of camera internal parameter calibration, external parameter calibration and the like, each acquisition point is determined on a three-dimensional coordinate system, acquisition control parameters such as exposure time, shutter speed, white balance and the like are set according to scene requirements and actual operation, and high-quality depth image data are obtained.
Based on the depth camera technology, according to acquired acquisition coordinates and depth image data, point cloud processing algorithm is utilized to extract and construct point cloud of the depth image data captured in the image acquisition device, preprocessing and optimizing are carried out through processing methods such as point cloud denoising, registration and feature extraction, point cloud data of all nodes are combined together, and a node size verification dataset is constructed, wherein the node size verification dataset comprises information such as position, shape and size of each node.
Based on the obtained depth image data, different surface characteristic information such as bulges, depressions, scratches and the like is extracted through a digital image processing technology and an image characteristic learning algorithm, various surface characteristic information is comprehensively considered, an intelligent algorithm and a machine learning model are utilized to realize rough characteristic recognition and description of the surface state, a rough characteristic recognition result is generated, rough characteristic recognition results of all nodes are combined with other relevant information to construct a surface state verification data set, and the surface state verification data set comprises information such as the position, the surface state characteristics, polishing control parameters and the like of each node.
Based on the constructed node size verification data set, the calibration control result is applied to the polishing control process of the actual node, feedback information and various index data are recorded, and based on the constructed surface state verification data set, the calibration control result is applied to the polishing control process of the actual workpiece, and the feedback information and various index data are recorded, so that the optimization condition of the surface state of the workpiece is evaluated. And (3) evaluating the effectiveness and feasibility of the calibration control result by analyzing and processing the feedback information and the index data, and adjusting and optimizing polishing control parameters and strategies by combining an intelligent algorithm and a self-adaptive learning technology so as to further improve the polishing control quality and efficiency.
Further, step S713 of the present application further includes:
step S7131: constructing a part identification feature of the tool clamp according to the standard data set;
step S7132: configuring fuzzy attenuation coefficients of node positions according to the M nodes;
step S7133: performing feature fuzzy adjustment of the part identification features according to the fuzzy attenuation coefficient;
step S7134: image feature matching of the corresponding nodes is executed through the part identification features after fuzzy adjustment, and the images are segmented into feature matching areas and fuzzy intersection areas according to matching results;
step S7135: and obtaining the roughness characteristic recognition result based on the segmentation result of the image.
Specifically, the depth image of the workpiece in the surface state verification data set is subjected to feature extraction and analysis by utilizing a computer vision technology, different features and attributes of each part, such as contours, lines, convexity and the like are extracted, and recognition models of different parts of the tool clamp are built according to the technologies of deep learning, neural networks and the like, and classification capacity of the recognition models is trained, so that the tool clamp parts can be accurately recognized. And matching the extracted surface state features with the tool clamp parts, calculating the fitting degree of each part, determining the feature area corresponding to each part, and recording.
Based on the construction of the surface state verification dataset, the depth image data are processed and analyzed by utilizing a computer vision technology and a digital image processing algorithm to obtain the information such as the surface quality, the geometric structure, the morphological attribute and the like of each node, the fuzzy attenuation coefficient of each node position is calculated by combining the surface state characteristics and the related information of each node through a fuzzy logic algorithm, and various factors such as the surface quality, the polishing difficulty, the importance degree and the like can be considered by the coefficient. The fuzzy attenuation coefficient of the node position is the polishing difficulty degree and the priority order of the node, namely the node which is harder to polish or more important is higher in the fuzzy attenuation coefficient, and the coefficient can be regarded as weight distribution for the importance of polishing tasks of each node.
Multiplying the characteristic values by the corresponding weights by utilizing the fuzzy attenuation coefficients of the constructed node positions, normalizing, comprehensively considering various factors such as surface states, workpiece forms, precision requirements and the like to obtain weighted characteristic values of each node, and carrying out fuzzy processing and correction on the weighted characteristic values so as to adapt to polishing scenes and task requirements.
According to the recorded node information and characteristic values, determining the position and characteristic descriptor of each node, matching the obtained node characteristic descriptor with the input image data, finding out the best matching node and the corresponding characteristic descriptor value, setting a threshold value by using fuzzy adjustment information in the matching process to judge the reliability of the matching result, and dividing the original image into a characteristic matching area and a fuzzy intersection area according to the matching result, wherein the criterion is that the matching result with higher reliability is selected. The feature matching areas refer to areas with high matching degree and obvious dominant effect of feature descriptors; whereas fuzzy intersection regions refer to those regions where there are multiple contribution of feature descriptors, the feature values of which may have been affected by fuzzy adjustment.
And constructing a corresponding roughness recognition model according to the part recognition features, and recognizing roughness feature values of each region by learning and classifying image feature data, wherein the feature values are used for evaluating the contact state of a cutter and the surface of a workpiece, so as to help control the polishing quality and avoid excessive loss of the cutter.
Further, step S7135 of the present application further includes:
Step S71351: respectively executing the void feature recognition of each divided area according to the dividing result, and recording the void size, the void quantity and the void distribution coordinates;
step S71352: performing roughness uniformity analysis on the segmented regions based on the void sizes and the void distribution coordinates, and generating first reference parameters of roughness;
step S71353: evaluating the roughness distribution density of the divided areas according to the number of the gaps and the gap distribution coordinates, and generating a second reference parameter of roughness;
step S71354: performing a roughness analysis of the tool pliers by the void size, generating a third reference parameter for roughness;
step S71355: and obtaining the roughness characteristic recognition result according to the first reference parameter, the second reference parameter and the third reference parameter.
Specifically, based on the void feature extraction technology, voids in each partition area around the cutter and the workpiece are detected and identified, indexes such as size, number and distribution condition of void areas are obtained, information such as processing quality, cutter use condition and workpiece surface state is reflected, and for fuzzy intersection areas, results of a plurality of feature descriptors are combined and adjusted based on statistical methods such as average value or maximum value, so that more accurate and reliable void features are obtained, and basis is provided for follow-up polishing control and quality evaluation.
And calculating corresponding indexes such as void density, void size variance, void spacing and the like by utilizing void size and distribution coordinate information, reflecting the roughness distribution condition on the processing surface, and carrying out preliminary analysis and evaluation on roughness uniformity in each divided area according to the indexes and combining the relation and weight among the void parameters to generate a first reference parameter of roughness.
And calculating corresponding indexes such as void distribution density, void size frequency and the like by using the void quantity and the distribution coordinate information, reflecting the roughness distribution condition on the processing surface, and evaluating the roughness distribution in each partition area based on the calculation result of the void distribution parameters according to the indexes to generate a second reference parameter of the roughness.
And calculating the surface roughness of the tool clamp by using the extracted gap size information, reflecting the contact quality between the tool clamp and the workpiece surface, and generating a third reference parameter of the roughness of the tool clamp according to the roughness parameters.
The first reference parameter, the second reference parameter and the third reference parameter obtained in the previous step are synthesized according to a certain weight to obtain an overall roughness characteristic recognition result, wherein the weights of different reference parameters can be set according to actual needs to reflect the importance of different parameters to roughness recognition.
Further, step S700 of the present application further includes:
step S700-1: setting an early warning stopping threshold;
step S700-2: when the auxiliary control information triggers the early warning stopping threshold value, a stopping control instruction is generated;
step S700-3: and re-performing polishing control planning of the tool pliers according to the stopping control instruction.
Specifically, according to actual conditions and requirements, a corresponding early warning stopping threshold value is set to reflect the processing quality level in the polishing control process. When the early warning stop threshold is triggered, auxiliary control information is automatically transmitted to a system for analysis and processing, and the information comprises processing data obtained through real-time monitoring, machine running states, part surface conditions and the like, so that subsequent judgment and analysis can be performed. The system compares and analyzes the collected processing data with a preset early warning stopping threshold value to determine whether the processing quality in the current state reaches the early warning stopping threshold value, if the analysis result confirms that the early warning stopping threshold value is triggered, a stopping control instruction is generated according to a preset program, and the polishing machine is informed to stop according to a safety flow. Meanwhile, the operator can be reminded of the situation through a human-computer interface or an alarm signal, and corresponding measures can be taken in time.
Specifically, the early warning stop threshold may be divided into two parts, namely an early warning threshold and a stop threshold, where the early warning threshold is set at a lower level, and when the processing quality reaches the threshold, the system will send out an early warning signal or alarm to prompt the operator to enhance monitoring and adjustment so as to avoid a larger drop in the processing quality. The early warning threshold adopts data obtained by offline model training as a standard reference value, and an early warning mechanism is started when the measured value exceeds a preset standard value through real-time measurement and monitoring. The stop threshold is set at a higher level and when the machining quality reaches the threshold, the system automatically stops the grinding process, so that the surface of the part is prevented from being damaged due to deep grinding. The stop threshold is typically determined by analysis of data obtained by offline model training, plus prior experimentation, expert experience, and the like.
The generated stop control command is analyzed and interpreted, the stop control command generally provides information about operation parameters, mode setting, early warning limit values and the like, so that the cause can be found, fault points can be removed, and a next control scheme can be determined. After the fault cause is determined, the polishing control plan is updated and adjusted according to the actual situation, including optimization and improvement on polishing equipment, cutting fluid, tool selection and the like, so as to meet new requirements and demands.
Further, as shown in fig. 3, the present application further includes:
step S810: carrying out polishing data recording on the tool pliers, and mapping a recording result and a quality detection result;
step S820: when the quality detection result meets a preset threshold value, a polishing control template is generated based on the polishing data, and a template similarity value is set;
step S830: and carrying out polishing control on the follow-up tool pliers according to the polishing control template and the template similarity value.
Specifically, in the actual production process, the key parameters and the change conditions of the tool pliers in the polishing process, such as the outline shape, the surface finish, the cutting edge size and the like, are recorded through the sensors, the monitoring equipment and the like, and meanwhile, the tool pliers are periodically detected and tested, including relevant physical characteristics, mechanical strength, surface quality and the like, and quality detection results are obtained, so that the machining quality and the performance meet the requirements. The recorded polishing data and quality detection results are mapped and analyzed, and specifically, the polishing data and quality detection results can be compared and verified through means of data visualization, statistical analysis and the like, so that the cause of the degradation of the processing quality is identified, the operation scheme is adjusted in a targeted manner, and the equipment performance is optimized.
The preset threshold value of quality detection is set by a manufacturer or a user according to the self requirements, and the preset threshold value comprises aspects of surface finish, cutting edge size, contour shape and the like, so that the product can achieve the expected processing effect. The recorded sanding data is processed and analyzed by data mining techniques to extract relevant characteristic information and regularity therefrom. Based on the processed sanding data, a corresponding sanding control template is generated and a similarity threshold is set for each template. The polishing control template is a normalized polishing operation guide, and comprises various contents such as processing parameters, processing flow, operation specifications and the like, so that the accuracy and the replicability of the operation are improved.
In actual operation, the polishing control template and the template similarity value are cited, the control template is directly used as an operation guide, equipment is controlled and optimized in a computer program mode and the like, meanwhile, data obtained in each operation are calculated and compared with the existing control template, and corresponding matching is carried out based on a statistical method and a pattern recognition technology. When the matching degree meets the requirement, the polishing process is controlled by various automatic equipment and programs, and subsequent adjustment and optimization are performed according to the actual situation.
In summary, the tool pliers polishing method and device based on sensor data interaction provided by the embodiment of the application have the following technical effects:
performing basic data interaction of the tool pliers, constructing a standard data set, including standard size constraint and surface roughness constraint, performing three-dimensional data scanning on blanks, constructing a three-dimensional fitting model, matching an identification center point, determining a three-dimensional contour, generating polishing size data, reading equipment parameters, constructing a control model, inputting the control model, outputting N control execution strategies, setting speed-quality balance data, performing strategy screening to obtain control parameters, controlling polishing equipment to perform polishing control of the tool pliers, performing polishing node image acquisition, generating auxiliary control information, performing real-time adjustment on the control parameters, and completing polishing control of the tool pliers according to real-time adjustment results. The method solves the technical problems that the traditional polishing method mainly depends on manual operation and experience accumulation, has the defects of low efficiency and easy error due to difficulty in adaptively adjusting polishing parameters according to real-time requirements, and cannot accurately and stably realize the target polishing effect, realizes the accurate control of the polishing process by utilizing sensor data interaction and real-time control, and carries out self-adaptive adjustment on the polishing parameters, thereby greatly improving the stability and consistency of the polishing effect and achieving the technical effects of improving the flexibility and the intelligent degree of machining.
Example 2
Based on the same inventive concept as the tool pliers polishing method based on sensor data interaction in the foregoing embodiments, as shown in fig. 4, the present application provides a tool pliers polishing device based on sensor data interaction, the device comprising:
the data interaction module 10 is used for performing basic data interaction of the tool pliers, and constructing a standard data set of the tool pliers according to the basic data, wherein the standard data set comprises standard size constraints and surface roughness constraints;
the data scanning module 20 is used for executing three-dimensional data scanning on a blank, constructing a three-dimensional fitting model according to a point cloud data set, matching an identification center point, determining a three-dimensional contour according to the three-dimensional fitting model and the identification center point, and generating polishing size data according to the three-dimensional contour and the standard data set;
the parameter reading module 30 is used for reading equipment parameters of polishing equipment and constructing a control model according to the equipment parameters;
the strategy output module 40 is used for inputting the polishing size data and the material data into the control model and outputting N control execution strategies;
The policy screening module 50 is configured to set speed-quality balance data, and perform policy screening of the N control execution policies based on the balance data to obtain control parameters;
the auxiliary information generation module 60 is used for controlling the polishing equipment to execute polishing control of the tool pliers based on the control parameters, executing node image acquisition of polishing through the image acquisition device, and generating auxiliary control information according to an image acquisition result;
and the polishing control module 70 is used for adjusting the control parameters in real time through the auxiliary control information, and finishing polishing control of the tool pliers according to the real-time adjustment result.
Further, the device further comprises:
the control fitting module is used for performing control fitting based on the control parameters and setting calibration control results of M nodes, wherein M is a positive integer greater than 2;
the depth image acquisition module is used for executing depth image acquisition of the tool pliers through the image acquisition device after polishing control of any node is completed, and constructing depth image data of the tool pliers node;
And the polishing control verification module is used for performing polishing control verification according to the calibration control result and the depth image data, and generating the real-time adjustment result based on the polishing control verification result.
Further, the device further comprises:
the acquisition control data acquisition module is used for acquiring acquisition coordinates and acquisition control data of the image acquisition device;
the point cloud data extraction module is used for extracting point cloud data of the node tool pliers according to the acquisition coordinates, the acquisition control data and the depth image data and constructing a node size verification data set;
the image feature analysis module is used for performing image feature analysis on the depth image data, generating a rough feature recognition result and constructing a surface state verification data set;
and the control verification module is used for carrying out control verification on the calibration control result through the node size verification data set and the surface state verification data set.
Further, the device further comprises:
the part identification feature construction module is used for constructing part identification features of the tool pliers according to the standard data set;
the fuzzy attenuation coefficient configuration module is used for configuring fuzzy attenuation coefficients of node positions according to the M nodes;
The characteristic fuzzy adjustment module is used for carrying out characteristic fuzzy adjustment of the part identification characteristic according to the fuzzy attenuation coefficient;
the image feature matching module is used for executing image feature matching of the corresponding nodes through the part identification features after the fuzzy adjustment, and dividing the image into a feature matching area and a fuzzy intersection area according to the matching result;
and the recognition result acquisition module is used for acquiring the roughness characteristic recognition result based on the segmentation result of the image.
Further, the device further comprises:
the void feature recognition module is used for respectively executing void feature recognition of each divided area according to the dividing result and recording void size, void quantity and void distribution coordinates;
the uniformity analysis module is used for carrying out roughness uniformity analysis on the divided areas based on the gap sizes and the gap distribution coordinates and generating first reference parameters of roughness;
the density evaluation module is used for evaluating the roughness distribution density of the divided areas according to the number of the gaps and the gap distribution coordinates, and generating a second reference parameter of roughness;
the roughness analysis module is used for executing the roughness analysis of the tool pliers through the gap size and generating a third reference parameter of roughness;
And the characteristic recognition result acquisition module is used for acquiring the roughness characteristic recognition result according to the first reference parameter, the second reference parameter and the third reference parameter.
Further, the device further comprises:
the threshold setting module is used for setting an early warning stopping threshold;
the stop control instruction generation module is used for generating a stop control instruction when the auxiliary control information triggers the early warning stop threshold value;
and the polishing control planning module is used for carrying out polishing control planning on the tool pliers again according to the stopping control instruction.
Further, the device further comprises:
the polishing data recording module is used for recording polishing data of the tool pliers and mapping a recording result and a quality detection result;
the control template generation module is used for generating a polishing control template based on the polishing data and setting a template similarity value when the quality detection result meets a preset threshold value;
and the follow-up polishing control module is used for carrying out polishing control on follow-up tool pliers according to the polishing control template and the template similarity value.
The foregoing detailed description of the tool pliers polishing method based on sensor data interaction will be clear to those skilled in the art, and the tool pliers polishing method and apparatus based on sensor data interaction in this embodiment, and the apparatus disclosed in the embodiments, because they correspond to the methods disclosed in the embodiments, are described in a relatively simple manner, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A tool pliers polishing method based on sensor data interaction, which is characterized by comprising the following steps:
performing basic data interaction of the tool pliers, and constructing a standard data set of the tool pliers according to the basic data, wherein the standard data set comprises standard size constraint and surface roughness constraint;
performing three-dimensional data scanning on a blank, constructing a three-dimensional fitting model according to a point cloud data set, matching an identification center point, determining a three-dimensional contour according to the three-dimensional fitting model and the identification center point, and generating polishing size data according to the three-dimensional contour and the standard data set;
Reading equipment parameters of polishing equipment, and constructing a control model according to the equipment parameters;
inputting the polishing size data and the material data into the control model, and outputting N control execution strategies;
setting speed-quality balance data, and performing strategy screening of the N control execution strategies based on the balance data to obtain control parameters;
controlling the polishing equipment to execute polishing control of the tool pliers based on the control parameters, executing node image acquisition of polishing through an image acquisition device, and generating auxiliary control information according to an image acquisition result;
and adjusting the control parameters in real time through the auxiliary control information, and finishing polishing control of the tool pliers according to the real-time adjustment result.
2. The method of claim 1, wherein the method further comprises:
performing control fitting based on the control parameters, and setting calibration control results of M nodes, wherein M is a positive integer greater than 2;
after polishing control of any node is completed, the image acquisition device is used for acquiring depth images of the tool pliers, and depth image data of the tool pliers nodes are constructed;
and performing polishing control verification according to the calibration control result and the depth image data, and generating the real-time adjustment result based on the polishing control verification result.
3. The method of claim 2, wherein the method further comprises:
acquiring acquisition coordinates and acquisition control data of the image acquisition device;
extracting point cloud data of the node tool pliers according to the acquisition coordinates, the acquisition control data and the depth image data, and constructing a node size verification data set;
performing image feature analysis on the depth image data, generating a rough feature recognition result, and constructing a surface state verification data set;
and carrying out control verification of the calibration control result through the node size verification data set and the surface state verification data set.
4. A method as claimed in claim 3, wherein the method further comprises:
constructing a part identification feature of the tool clamp according to the standard data set;
configuring fuzzy attenuation coefficients of node positions according to the M nodes;
performing feature fuzzy adjustment of the part identification features according to the fuzzy attenuation coefficient;
image feature matching of the corresponding nodes is executed through the part identification features after fuzzy adjustment, and the images are segmented into feature matching areas and fuzzy intersection areas according to matching results;
And obtaining the roughness characteristic recognition result based on the segmentation result of the image.
5. The method of claim 4, wherein the method further comprises:
respectively executing the void feature recognition of each divided area according to the dividing result, and recording the void size, the void quantity and the void distribution coordinates;
performing roughness uniformity analysis on the segmented regions based on the void sizes and the void distribution coordinates, and generating first reference parameters of roughness;
evaluating the roughness distribution density of the divided areas according to the number of the gaps and the gap distribution coordinates, and generating a second reference parameter of roughness;
performing a roughness analysis of the tool pliers by the void size, generating a third reference parameter for roughness;
and obtaining the roughness characteristic recognition result according to the first reference parameter, the second reference parameter and the third reference parameter.
6. The method of claim 1, wherein the method further comprises:
setting an early warning stopping threshold;
when the auxiliary control information triggers the early warning stopping threshold value, a stopping control instruction is generated;
and re-performing polishing control planning of the tool pliers according to the stopping control instruction.
7. The method of claim 1, wherein the method further comprises:
carrying out polishing data recording on the tool pliers, and mapping a recording result and a quality detection result;
when the quality detection result meets a preset threshold value, a polishing control template is generated based on the polishing data, and a template similarity value is set;
and carrying out polishing control on the follow-up tool pliers according to the polishing control template and the template similarity value.
8. A tool pliers polishing device based on sensor data interaction for implementing the tool pliers polishing method based on sensor data interaction according to claims 1-7, comprising:
the data interaction module is used for performing basic data interaction of the tool pliers and constructing a standard data set of the tool pliers according to the basic data, wherein the standard data set comprises standard size constraint and surface roughness constraint;
the data scanning module is used for executing three-dimensional data scanning on a blank, constructing a three-dimensional fitting model according to a point cloud data set, matching an identification center point, determining a three-dimensional contour according to the three-dimensional fitting model and the identification center point, and generating polishing size data according to the three-dimensional contour and the standard data set;
The parameter reading module is used for reading equipment parameters of polishing equipment and constructing a control model according to the equipment parameters;
the strategy output module is used for inputting the polishing size data and the material data into the control model and outputting N control execution strategies;
the strategy screening module is used for setting speed-quality balance data, and carrying out strategy screening of the N control execution strategies based on the balance data to obtain control parameters;
the auxiliary information generation module is used for controlling the polishing equipment to execute polishing control of the tool pliers based on the control parameters, executing node image acquisition of polishing through the image acquisition device and generating auxiliary control information according to an image acquisition result;
and the polishing control module is used for adjusting the control parameters in real time through the auxiliary control information and finishing polishing control of the tool pliers according to the real-time adjustment result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311238910.9A CN117047569A (en) | 2023-09-25 | 2023-09-25 | Tool clamp polishing method and device based on sensor data interaction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311238910.9A CN117047569A (en) | 2023-09-25 | 2023-09-25 | Tool clamp polishing method and device based on sensor data interaction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117047569A true CN117047569A (en) | 2023-11-14 |
Family
ID=88662960
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311238910.9A Pending CN117047569A (en) | 2023-09-25 | 2023-09-25 | Tool clamp polishing method and device based on sensor data interaction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117047569A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117655861A (en) * | 2023-12-29 | 2024-03-08 | 上海开恒光岳机械制造有限公司 | Intelligent matching system for shuttle valve production |
| CN118411379A (en) * | 2024-05-08 | 2024-07-30 | 江苏中科云控智能工业装备有限公司 | Automatic deburring process feedback optimization system and method |
-
2023
- 2023-09-25 CN CN202311238910.9A patent/CN117047569A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117655861A (en) * | 2023-12-29 | 2024-03-08 | 上海开恒光岳机械制造有限公司 | Intelligent matching system for shuttle valve production |
| CN118411379A (en) * | 2024-05-08 | 2024-07-30 | 江苏中科云控智能工业装备有限公司 | Automatic deburring process feedback optimization system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117047569A (en) | Tool clamp polishing method and device based on sensor data interaction | |
| CN110434671B (en) | Cast member surface machining track calibration method based on characteristic measurement | |
| CN111468989B (en) | Five-axis linkage numerical control manipulator polishing control system and method | |
| CN115035120B (en) | Machine tool control method and system based on Internet of things | |
| CN116823826B (en) | Numerical control machine tool tipping abnormity detection method | |
| CN114041168A (en) | Automated 360-degree dense point object inspection | |
| EP3736648B1 (en) | Method for autonomous optimization of a grinding process | |
| CN118134062B (en) | Numerical control machine tool casting quality tracking system | |
| JP3427389B2 (en) | Deburring method and device | |
| CN114488943B (en) | Random multi-area efficient polishing path planning method oriented to matched working conditions | |
| CN116909208B (en) | Shell processing path optimization method and system based on artificial intelligence | |
| CN118081767A (en) | Automatic programming system and method for post-processing machining of casting robot | |
| CN112008543B (en) | Abnormal grinding diagnosis method for electrode cap of welding gun | |
| CN114972948A (en) | Neural detection network-based identification and positioning method and system | |
| CN117115143B (en) | Method and device for detecting wafer core particle, computer equipment and storage medium | |
| CN117171922B (en) | Method and system for parallel correction in steel structure manufacturing | |
| CN118334087B (en) | Visual alignment calibration method, device, equipment and storage medium | |
| CN116912241B (en) | CNC machine adjustment optimization method and system based on machine learning | |
| CN118070983B (en) | Industrial machinery production optimization method and system based on deep learning | |
| CN118493088A (en) | Intelligent polishing and polishing path planning method | |
| CN118905741A (en) | Ceramic riving knife size polishing method, equipment and storage medium based on image analysis | |
| CN114800034B (en) | Intelligent tool setting system and method for numerical control machine tool adopting machine vision | |
| JP7455271B2 (en) | Machining program correction device, machining program correction method, and machining system | |
| CN118938805A (en) | Automatic processing method, device and equipment for arc-shaped workpiece and storage medium | |
| CN117206984A (en) | Automatic identification polishing method, system, equipment and storage medium based on neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |