Intelligent control system and method of high-precision numerical control machine tool
By using deep learning analytics to acquire machining data from CNC machine tools in real time, the problem of position detection in the automatic tool setting control system for tool blocks has been solved, enabling efficient machining prediction and precision control, and improving the production efficiency and accuracy of CNC machine tools.
Patent Information
- Application Number
- CN202410987179.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-23
- Publication Date
- 2024-11-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In existing automatic tool setting control systems for CNC machine tools, it is difficult to detect the starting machining point position of the tool on the workpiece, which requires repeated trial cutting and reduces machining efficiency.
By employing deep learning analysis technology, through visual information acquisition, image data processing, data fusion analysis, and laser detection modules, the position data of the machining tool and the workpiece are acquired in real time, the machining deviation is calculated and predicted, and the movement distance is truncated within a preset time to generate a prediction model to improve tool setting accuracy and efficiency.
It improves the processing efficiency of CNC machine tools, reduces auxiliary time, saves production costs, and can predict and handle positional deviations in advance to ensure processing accuracy.
Smart Images

Figure CN118938810A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent manufacturing technology, and in particular to an intelligent control system and method for a high-precision CNC machine tool. Background Art
[0002] As the mother machine of industry, the safe and stable operation and high-quality process of CNC machine tools are the key to realizing intelligent manufacturing. Among them, tool setting is an important operation step in CNC machining. Keep the zero point alignment before starting the CNC lathe, and use G54-G59 to set the workpiece zero point. To a certain extent, the accuracy of tool setting can determine the machining accuracy of the parts. At the same time, the efficiency of tool setting also directly affects the efficiency of CNC machining. With the development of manufacturing technology, mechanical machining has gradually entered the stage of automation and intelligence. The original tool setting method has been difficult to meet the needs of further development of manufacturing technology in terms of tool setting accuracy and efficiency. Therefore, exploring a new tool setting method can effectively improve machining accuracy and save tool setting time, making production more efficient.
[0003] Under the existing technology, manual tool setting and automatic tool setting with tool setting blocks are dominant, among which automatic tool setting with tool setting blocks is the mainstream operation mode. In the case of automatic tool setting with tool setting blocks, the common method is to pre-establish a mapping relationship between the tool setting angle and the position interval of the workpiece, and input coordinate data for tool setting. In reality, the actual cutting time only accounts for about 55% of the total processing time, while auxiliary time such as tool clamping and tool setting accounts for 45% of the processing time. However, in the automatic tool setting control system of the tool setting block in the existing technology, the position of the starting processing point of the tool on the part is not easy to detect, resulting in the method in actual production to first perform a trial cutting and then adjust the tool according to the detected processing deviation. This process generally needs to be repeated at least 1 to 2 times to complete the tool setting. In this case, the processing efficiency of the CNC machine tool is reduced, which is not conducive to the company saving production time costs. Summary of the invention
[0004] In view of the above-mentioned problems existing in the existing field of intelligent manufacturing technology, the present invention is proposed.
[0005] Therefore, one of the objects of the present invention is to provide an intelligent control system and method for a high-precision CNC machine tool, which utilizes deep learning analysis technology to obtain the axis coordinate data of the processing tool at different original positions and the coordinate data of the required processing points on the workpiece to be processed within a preset time, and calculate the distance between the two coordinate data. At the same time, the movement distance of the processing tool is collected within the preset time, and it is calculated to determine whether the processing tool will cause position deviation when it reaches the required processing point within this time. Moreover, within the preset time, the movement distance data of the processing tool up to the truncation time can be cut off. Therefore, if necessary, it can be calculated and predicted as early as possible whether the processing tool will cause position deviation when it reaches the required processing point at its original position, which is beneficial to improving work efficiency.
[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:
[0007] In one aspect, the present invention provides an intelligent control system for a high-precision CNC machine tool, comprising:
[0008] A visual information acquisition module, used to acquire real-time on-site visual information provided by a preset CNC machine tool, wherein the visual information includes the size of a tool holder of the preset CNC machine tool, the perimeter of a workpiece to be processed, and the original distance data between the processing tool and the workpiece to be processed, and the visual information acquisition module includes a CCD camera;
[0009] An image data processing module, the image data processing module comprising an image data compression module for compressing and processing the image data of the CCD camera, and an image interception module for intercepting image data of a preselected area in the image data compression module;
[0010] A data fusion analysis unit, wherein the image data analysis unit includes a scanning module, a calculation module, a storage module and an analysis module;
[0011] The scanning module is used to scan the flatness of the workpiece to be processed in real time on site, and the flatness to be scanned includes the flatness data of the upper and lower end surfaces of the workpiece to be processed;
[0012] The calculation module calculates the flatness difference of the workpiece to be processed based on the flatness data scanned and acquired by the scanning module;
[0013] The storage module is used to store the flatness difference data calculated by the calculation module and build a cloud database;
[0014] The analysis module is used to analyze the distance between the edge point of the machining dimension and the nearest flatness difference based on the center point of the workpiece to be machined;
[0015] An axis coordinate acquisition module is used to acquire the distance between the machining tool and the machining point of the workpiece to be machined at different orientations, wherein the distance is the horizontal coordinate distance, and preset the machining tool orientation data and the orientation data of the machining point to be machined, construct a three-dimensional horizontal distance model, and acquire the flatness difference data between different machining points and the nearest ones;
[0016] A laser detection module, the laser detection module comprising a laser sensor for measuring the distance of laser oblique projection during the movement of the machining knife, an angle sensor for detecting the inclination angle value of the laser sensor, and an A / D conversion circuit for converting an analog signal of the laser sensor;
[0017] The visual data capture module uses the previous position data of the processing tool as a base point to capture the distance moved by the processing tool to the point to be processed within a unit moving time, and obtains the spacing between the distance and the point to be processed based on the moving distance. At the same time, the moving distance within the unit moving time is divided to generate a prediction model.
[0018] As a preferred solution of the present invention, in the visual information acquisition module, the original distance data includes the height data of the processing tool and the workpiece to be processed and the orientation data of the processing tool based on the workpiece to be processed, and other required processing points are obtained based on the center point of the workpiece to be processed, and the processing points are arranged according to θ 1 ,θ 2 , ..., θ n The time required for the machining tool to reach the preset machining point and the center point of the workpiece to be machined from the original position is calculated according to the following formula:
[0019] Where T represents the unit moving time;
[0020] Where, T k represents the moving time required for the machining tool to move to the kth machining point; C k represents the distance between the kth preset processing point and the coordinate trajectory of the processing tool, η represents the friction function during the movement of the processing tool, and η i represents the friction function collected during the i-th movement of the machining tool;
[0021] On the basis of the above, the time required for the machining tool to move from the original position to the center point of the workpiece to be machined is calculated according to the following formula:
[0022] Among them, T k represents the moving time required for moving to the kth processing point based on the processing tool;
[0023] represents the coordinate trajectory distance between the center point of the workpiece to be processed and the processing tool obtained based on the perimeter data of the workpiece to be processed, δ i represents the original position data of the machining tool relative to the center point of the workpiece to be machined, measured for the i-th time before starting machining.
[0024] As a preferred solution of the present invention, the friction functions of the processing tool during the movement are collected, and the size of the collected friction function is divided into intervals of 2N / ㎡ to 5N / ㎡, 5N / ㎡ to 8N / ㎡ and 8N / ㎡ to 10N / ㎡, and the distance moved by the processing tool to the center point of the workpiece to be processed and / or the preset processing point in the unit movement time under different interval friction functions is obtained, and the distance is calculated according to the following formula:
[0025] Wherein, x represents the total unit movement time of the processing knife;
[0026] In the formula, p i represents the i-th collected moving distance data based on the total unit moving time of the processing knife, j represents the cutoff distance data, and the cutoff distance data is cut off based on the moving distance data of the total unit moving time of the processing knife, x represents the preset moving distance under the total unit moving time minus the actual moving distance of the processing knife, d vi It represents the i-th collected moving time of the processing tool in the case of the v-th moving line trajectory.
[0027] As a preferred solution of the present invention, the truncation distance data obtained based on the total unit movement time of the processing knife is divided into first truncation distance data, second truncation distance data and third truncation distance data in a step-by-step manner, and the first truncation distance data, the second truncation distance data and the third truncation distance data are all incremental data, and the distance data moved by the processing knife within the total unit movement time is obtained, and based on the distance data, combined with the total unit movement time, the average truncation distance data is calculated as follows:
[0028] Among them, f k It represents the total moving distance of the machining tool collected during the total moving time of the kth unit;
[0029] Where n is the time for collecting and / or intercepting the cutoff distance data, It represents the cutoff distance data obtained at the i-th collection and / or interception time, wherein a safety threshold is preset based on the minimum cutoff distance data. When the cutoff distance data of the processing knife movement in the future time period is less than the safety threshold, the system determines that it is in an abnormal state and issues an abnormal state alarm, otherwise, no determination is made.
[0030] As a preferred solution of the present invention, a data pool is constructed for the collected and / or intercepted cutoff distance data below the safety threshold, and the data in the data pool is divided into several evaluation indicators by labeling, the evaluation indicator data in the data pool is counted, and the data is normalized, and the weight of each evaluation indicator data in the safety threshold is analyzed.
[0031] As a preferred solution of the present invention, wherein: in the scanning module, it includes scanning the flatness next to the center point of the workpiece to be processed, specifically by pre-acquiring the diameter length data and / or circumference data of the center point after processing, and presetting a critical threshold based on the diameter length data and / or circumference data and the minimum safety distance at the uneven point. When the minimum safety distance scanned by the scanning module is lower than the critical threshold, the system determines that the processing operation is in an abnormal state and issues an abnormal state warning, otherwise, no determination is made.
[0032] As a preferred solution of the present invention, based on the evaluation index data in the data pool, the processing tool movement friction data corresponding to the evaluation index data is obtained, and an early warning model is generated based on different friction data; based on the early warning model, a hierarchical management plan corresponding to different levels of the evaluation index data is formulated through evidence-based and Delphi methods.
[0033] As a preferred solution of the present invention, in the analysis module, the distance between the edge point of the processed size and the nearest flatness difference is divided into Among them, n represents the nth flatness difference distance data, and a matching model is generated based on historical data of the same orientation and the same processing size. The matching model includes distance data corresponding to the minimum flatness difference of the edge point of the processing size. When the distance data corresponding to the minimum flatness difference of the edge point of the processing size with the center point in the future time period is greater than the distance data corresponding to the minimum flatness difference of the edge point of the processing size in the matching model, the system determines that the analysis result is abnormal, otherwise, it will not be determined.
[0034] As a preferred solution of the present invention, the scanning module further includes scanning the shape of the uneven points near the center point and / or the preset processing point of the workpiece to be processed, obtaining the scanned image data, and analyzing and comparing the scanned image data to obtain the point of the shape at the uneven point closest to the center point and / or the preset processing point, and analyzing and calculating whether the closest point is lower than the critical threshold. When the minimum safety distance scanned by the scanning module is lower than the critical threshold, the system determines that the processing operation is in an abnormal state and issues an abnormal state warning. Otherwise, no determination is made.
[0035] On the other hand, the present invention provides a method for an intelligent control system of a high-precision CNC machine tool, comprising the following steps:
[0036] Acquire real-time on-site visual information provided by a preset CNC machine tool, including the preset CNC machine tool tool holder size, the perimeter of the workpiece to be processed, and the original distance data between the processing tool and the workpiece to be processed;
[0037] Compressing the acquired visual information image data, and intercepting the preselected area image data in the compressed image data;
[0038] Analyze the flatness of the workpiece to be processed in the acquired preselected area image data, calculate the flatness difference of the workpiece to be processed according to the acquired flatness data, and build a cloud database based on the acquired flatness difference data;
[0039] Taking the center point of the workpiece to be processed as a reference, analyzing the distance between the edge point of the processing dimension and the nearest flatness difference;
[0040] Obtaining the distance between the machining tool and the machining point of the workpiece to be machined at different orientations, presetting the machining tool orientation data and the orientation data of the machining point to be machined, constructing a three-dimensional lateral distance model, and simultaneously obtaining the flatness difference data of different machining points and the nearest ones;
[0041] The positioning data of the processing tool at all times are used as a base point to intercept the distance moved by the processing tool to the processing point within a unit moving time, and the distance between the distance and the processing point is obtained based on the moving distance, and the moving distance within the unit moving time is divided to generate a prediction model;
[0042] Based on the center point of the workpiece to be processed, other required processing points are obtained, the coordinate positions of the different processing points are obtained, the time required for the processing tool to move from the original position to the preset processing point and the center point of the workpiece to be processed is calculated, and the moving distance of the processing tool within the time range is obtained. The moving distance can be truncated and a safety threshold is preset. When the selected truncation distance data is less than the safety threshold, the system determines that it is in an abnormal state and issues an abnormal state alarm. Otherwise, no determination is made.
[0043] Beneficial effects:
[0044] The present invention utilizes deep learning analysis technology to obtain the axis coordinate data of the processing tool at different original orientations and the coordinate data of the processing point required on the workpiece to be processed within a preset time, and calculates the distance between the two coordinate data. At the same time, the movement distance of the processing tool is collected within the preset time, and it is calculated to determine whether the processing tool will cause position deviation when it reaches the required processing point within this time. Moreover, within the preset time, the movement distance data of the processing tool up to the truncation time can be cut off. Therefore, if necessary, it can be calculated and predicted as early as possible whether the processing tool will cause position deviation when it reaches the required processing point from its original orientation. This is beneficial to improving operating efficiency and helping enterprises save production time costs. At the same time, when it is calculated and predicted that a position deviation will occur, the causes of the position deviation, including the factor of friction resistance, can be analyzed, and an emergency management plan can be formulated, thereby further enabling the processing operations to proceed in an orderly manner and improving operating efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:
[0046] Figure 1 Schematic diagram of the modular structure of the intelligent control system of the high-precision CNC machine tool in the embodiment of the present invention;
[0047] Figure 2 Schematic diagram of the modular structure of the data fusion analysis unit in an embodiment of the present invention;
[0048] Figure 3 Schematic diagram of the modular structure of the laser detection module in an embodiment of the present invention;
[0049] Figure 4 A schematic diagram of a method flow of an embodiment of the present invention;
[0050] Figure 5 It is a schematic diagram of the process structure of an embodiment of the present invention;
[0051] Numbers in the figure: 110-visual information acquisition module; 1101-CCD camera; 120-image data processing module; 1201-image data compression module; 1202-image capture module; 130-data fusion analysis unit; 1301-scanning module; 1302-calculation module; 1303-storage module; 1304-analysis module; 140-axis coordinate acquisition module; 150-laser detection module; 1501-laser sensor; 1502-angle sensor; 1503-A / D conversion circuit; 160-visual data capture module. DETAILED DESCRIPTION
[0052] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.
[0053] Since the position of the starting processing point of the tool on the part is difficult to detect in the automatic tool setting control system of the existing tool block, the actual production method is to perform a trial cutting first, and then adjust the tool according to the detected processing deviation. This process generally needs to be repeated at least 1 to 2 times to complete the tool setting. In this case, the processing efficiency of the CNC machine tool is reduced, which is not conducive to the company saving production time costs.
[0054] Based on this, the present invention proposes an intelligent control system and method for a high-precision CNC machine tool, which utilizes deep learning analysis technology to cut off the moving distance data of the machining tool at the cut-off time within a preset time. If necessary, it can calculate and predict in advance whether the machining tool will have a position deviation when it reaches the required machining point from its original position, which is beneficial to improving work efficiency.
[0055] The present invention is further described in detail below through embodiments and in conjunction with the accompanying drawings.
[0056] Embodiment 1
[0057] Reference Figures 1 to 3 , is an embodiment of the present invention, which provides an intelligent control system for a high-precision CNC machine tool, comprising:
[0058] A visual information acquisition module 110 is used to acquire real-time on-site visual information provided by a preset CNC machine tool, wherein the visual information includes the size of a tool holder of the preset CNC machine tool, the perimeter of a workpiece to be processed, and the original distance data between the processing tool and the workpiece to be processed, and the visual information acquisition module includes a CCD camera 1101;
[0059] It should be noted that in this embodiment, the original distance data includes height data of the machining tool and the workpiece to be machined and position data of the machining tool based on the workpiece to be machined;
[0060] At the same time, further, based on the center point of the workpiece to be processed, other required processing points are obtained, and the processing points are arranged according to θ 1 ,θ 2 , ..., θ nDivide, where n represents the nth processing point, obtain the coordinate positions of different processing points, calculate the time required for the processing tool to reach the preset processing point and the center point of the workpiece to be processed from the original position, and calculate the time required for the processing tool to reach the preset processing point of the workpiece to be processed from the original position according to the following formula:
[0061] Where T represents the unit moving time;
[0062] Where, T k represents the moving time required to move to the kth processing point based on the processing tool; C k represents the distance between the kth preset processing point and the coordinate trajectory of the processing tool, η represents the friction function during the movement of the processing tool, and η i represents the friction function collected during the i-th movement of the machining tool;
[0063] On the basis of the above, the time required for the machining tool to move from the original position to the center point of the workpiece to be machined is calculated according to the following formula:
[0064] Among them, T k It represents the moving time required to move to the kth processing point based on the processing tool;
[0065] represents the coordinate trajectory distance between the center point of the workpiece to be processed and the machining tool based on the perimeter data of the workpiece to be processed, δ i represents the original position data of the machining tool relative to the center point of the workpiece to be machined, measured before the start of the i-th machining;
[0066] On the basis of the above, the friction functions of the machining tool during the movement are further collected, and the size of the collected friction function is divided into intervals of 2N / ㎡~5N / ㎡, 5N / ㎡~8N / ㎡ and 8N / ㎡~10N / ㎡. The distance moved by the machining tool to the center point of the workpiece to be processed and / or the preset processing point in the unit movement time under different interval friction functions is obtained, and the result is calculated according to the following formula:
[0067] Among them, x represents the total unit movement time of the machining tool;
[0068] In the formula, p i represents the i-th collected moving distance data based on the total unit moving time of the machining tool, j represents the cutoff distance data, which is intercepted based on the moving distance data of the total unit moving time of the machining tool, x represents the preset moving distance under the total unit moving time minus the actual moving distance of the machining tool, d vi It represents the i-th collected moving time of the machining tool in the v-th moving line trajectory;
[0069] Among them, this embodiment further divides the truncation distance data obtained based on the total unit movement time of the processing knife into first truncation distance data, second truncation distance data and third truncation distance data in a step-by-step manner, and the first truncation distance data, the second truncation distance data and the third truncation distance data are all incremental data, and obtains the distance data moved by the processing knife within the total unit movement time, and based on the distance data, combined with the total unit movement time, calculates the average truncation distance data, as follows:
[0070] Among them, f k It represents the total moving distance of the machining tool collected during the total moving time of the kth unit;
[0071] Where n is the time for collecting and / or intercepting the cutoff distance data, It represents the cutoff distance data obtained at the i-th collection and / or interception time, wherein a safety threshold is preset based on the minimum cutoff distance data. When the cutoff distance data of the processing knife movement in the future time period is less than the safety threshold, the system determines that it is in an abnormal state and issues an abnormal state alarm, otherwise, no determination is made.
[0072] On the basis of the above, this embodiment constructs a data pool for the collected and / or intercepted cutoff distance data below the safety threshold, and divides the data in the data pool into several evaluation indicators through annotation, calculates the evaluation indicator data in the data pool, normalizes the data, and analyzes the weight of each evaluation indicator data in the safety threshold;
[0073] On the basis of the above, this embodiment specifically obtains the processing tool movement friction data corresponding to the evaluation index data based on the evaluation index data in the data pool, and generates an early warning model based on different friction data. Based on the early warning model, a hierarchical management plan corresponding to different evaluation index data levels is formulated through evidence-based and Delphi methods.
[0074] An image data processing module 120, the image data processing module includes an image data compression module 1201 for compressing and processing image data of a CCD camera, and an image interception module 1202 for intercepting image data of a preselected area in the image data compression module;
[0075] The data fusion analysis unit 130, the image data analysis unit includes a scanning module 1301, a calculation module 1302, a storage module 1303 and an analysis module 1304;
[0076] The scanning module 1301 is used for real-time on-site scanning of the flatness of the workpiece to be processed. The flatness to be scanned includes the flatness data of the upper and lower end surfaces of the workpiece to be processed.
[0077] Specifically, this embodiment includes scanning the flatness of the workpiece to be processed near the center point, specifically by pre-acquiring the diameter length data and / or circumference data of the center point after processing, and presetting a critical threshold based on the diameter length data and / or circumference data and the minimum safety distance at the uneven point. When the minimum safety distance scanned by the scanning module is lower than the critical threshold, the system determines that the processing operation is in an abnormal state and issues an abnormal state warning. Otherwise, no determination is made.
[0078] This embodiment also includes scanning the flatness around the preset processing point, specifically by pre-acquiring the diameter length data and / or circumference data of the preset processing point after processing, and presetting a critical threshold based on the diameter length data and / or circumference data and the minimum safety distance at the uneven point. When the minimum safety distance scanned by the scanning module is lower than the critical threshold, the system determines that the processing operation is in an abnormal state and issues an abnormal state warning, otherwise, no determination is made;
[0079] It should be noted that in real life, the shapes of holes to be processed are not consistent. Sometimes they are perfect circles, sometimes they are ellipses, sometimes they are polygons and / or other irregular holes. Therefore, it is necessary to collect and scan the length of the processed hole, which improves adaptability.
[0080] On the basis of the above, further, the present embodiment also includes scanning the shape of the uneven points near the center point and / or the preset processing point of the workpiece to be processed, obtaining the scanned image data, and analyzing and comparing the scanned image data to obtain the point of the shape at the uneven point closest to the center point and / or the preset processing point, and analyzing and calculating whether the nearest point is below a critical threshold. When the minimum safety distance scanned by the scanning module is lower than the critical threshold, the system determines that the processing operation is in an abnormal state and issues an abnormal state warning. Otherwise, no determination is made.
[0081] The calculation module 1302 calculates the flatness difference of the workpiece to be processed based on the flatness data scanned and acquired by the scanning module 1301;
[0082] What needs to be further explained in this embodiment is that, specifically, the center point of the workpiece to be processed is used as a reference to extend to the upper, lower, left and right ends of the workpiece to be processed, wherein the flatness difference at any end is divided into data layers, and any data layer is preset as an extension critical point, and the height difference between the extension critical point and the center point of the workpiece to be processed is calculated.
[0083] The storage module 1303 is used to store the flatness difference data calculated by the calculation module 1302 and build a cloud database;
[0084] The analysis module 1304 is used to analyze the distance between the edge point of the machining dimension and the nearest flatness difference based on the center point of the workpiece to be machined;
[0085] It should be noted that in this embodiment, the distance of the flatness difference closest to the edge point of the machining dimension is the first extended critical point data extending from the center point of the workpiece to be machined to the upper, lower, left and right ends thereof, and the edge point of the machining dimension is the edge point of the machining location after the machining is completed;
[0086] It should also be emphasized in this embodiment that the distance between the edge point of the processed size and the nearest flatness difference is divided into Among them, n represents the nth flatness difference distance data, and a matching model is generated based on the historical data of the same orientation and the same processing size. The matching model includes distance data corresponding to the minimum flatness difference of the edge point of the processing size. When the distance data corresponding to the minimum flatness difference of the edge point of the processing size with the center point in the future time period is greater than the distance data corresponding to the minimum flatness difference of the edge point of the processing size in the matching model, the system determines that the analysis result is abnormal, otherwise, it will not be determined.
[0087] The axis coordinate acquisition module 140 is used to obtain the distance between the machining tool and the machining point of the workpiece to be machined at different positions, the distance is the horizontal coordinate distance, and presets the machining tool position data and the machining point position data, constructs a three-dimensional horizontal distance model, and obtains the flatness difference data between different machining points and the nearest ones;
[0088] It should be noted that in this embodiment, the flatness difference data between the point to be processed and the nearest point to it includes dividing the processing tool orientation data based on the center point of the workpiece to be processed, dividing the processing tool orientation data into four ends of upper, lower, left and right based on the center point of the workpiece to be processed, determining which end of the four ends of upper, lower, left and right the processing tool orientation is located at, and obtaining the flatness difference data of one end;
[0089] The laser detection module 150 includes a laser sensor 1501 for measuring the distance of laser oblique projection during the movement of the machining tool, an angle sensor 1502 for detecting the inclination angle value of the laser sensor, and an A / D conversion circuit 1503 for converting the analog signal of the laser sensor 1501;
[0090] The visual data capture module 160 uses the previous position data of the processing tool as a base point to capture the distance that the processing tool moves toward the point to be processed within a unit moving time, and obtains the spacing between the distance and the point to be processed based on the moving distance. At the same time, the moving distance within the unit moving time is divided to generate a prediction model.
[0091] Based on the above, the present application utilizes deep learning analysis technology to obtain the axis coordinate data of the processing tool at different original positions and the coordinate data of the processing points required on the workpiece to be processed within a preset time, and collect the movement distance of the processing tool within a preset time, and calculate and determine whether the processing tool will cause position deviation when it reaches the required processing point within this time. Moreover, within the preset time, the movement distance data of the processing tool up to the truncation time can also be cut off, so that if necessary, it can be calculated and predicted as early as possible whether the processing tool will cause position deviation when it reaches the required processing point from its original position, which is beneficial to improving work efficiency.
[0092] Embodiment 2
[0093] Reference Figure 4 , is an embodiment of the present invention. This embodiment combines the intelligent control system of the high-precision CNC machine tool and proposes a working method of the system as follows:
[0094] Acquire real-time on-site visual information provided by a preset CNC machine tool, including the preset CNC machine tool tool holder size, the perimeter of the workpiece to be processed, and the original distance data between the processing tool and the workpiece to be processed;
[0095] Compressing the acquired visual information image data, and intercepting the preselected area image data in the compressed image data;
[0096] Analyze the flatness of the workpiece to be processed in the acquired preselected area image data, calculate the flatness difference of the workpiece to be processed according to the acquired flatness data, and build a cloud database based on the acquired flatness difference data;
[0097] Taking the center point of the workpiece to be processed as the reference, analyze the distance between the edge point of the processing dimension and the nearest flatness difference;
[0098] Obtain the distance between the machining tool and the machining point of the workpiece to be machined at different positions, preset the machining tool position data and the machining point position data, build a three-dimensional lateral distance model, and simultaneously obtain the flatness difference data of different machining points and the nearest ones;
[0099] The positioning data of the machining tool at all times is used as the base point to intercept the distance that the machining tool moves to the point to be processed within a unit moving time, and the distance between the distance and the point to be processed is obtained based on the moving distance. At the same time, the moving distance within the unit moving time is divided to generate a prediction model;
[0100] Based on the center point of the workpiece to be processed, other required processing points are obtained, the coordinate positions of different processing points are obtained, the time required for the processing tool to move from the original position to the preset processing point and the center point of the workpiece to be processed is calculated, and the moving distance of the processing tool within the time range is obtained. The moving distance can be truncated and a safety threshold is preset. When the selected truncation distance data is less than the safety threshold, the system determines that it is in an abnormal state and issues an abnormal state alarm. Otherwise, no determination is made.
[0101] Embodiment 3
[0102] Reference Figure 5 , is an embodiment of the present invention, which provides an intelligent control method for a high-precision CNC machine tool. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.
[0103] In this embodiment, a specific use experiment is conducted on the method of the present invention. Under a preset identical experimental environment, two groups of experiments are conducted on the existing traditional method and the method of this embodiment, respectively. The specific experimental results are shown in Table 1 and Table 2.
[0104] Some of the jobs meet the requirements, as follows:
[0105] Axis coordinate data of machining tool during operation: original data of any axis coordinate in history;
[0106] State data of the workpiece to be processed: the workpiece to be processed must be perpendicular to the processing tool;
[0107] Power supply requirements: Normally supply the power required for the entire operating process of CNC machine tools.
[0108] Table 1 Comparison of tool setting accuracy under intelligent control data collection
[0109]
[0110]
[0111] Table 2 Comparison of cutoff distance data under intelligent control data collection
[0112]
[0113] Through the above experimental comparison, it can be determined that the intelligent control method provided by the present invention can not only obtain the moving distance required by the processing tool in different original positions according to different processing positions within the preset time, but also can truncate the moving distance data of the processing tool within the preset time, and then analyze and determine whether the moving distance within the truncated unit time meets the required total moving distance. This method is beneficial to improving the processing efficiency.
[0114] In actual use, although lubrication of metal structural parts is provided in the CNC machine tool, the high temperature generated during the continuous operation of the CNC machine tool will cause the lubricating oil to evaporate to a certain extent. In this case, if the lubricating oil required for certain gaps is not replenished in time, the friction resistance of the movement of parts in the CNC machine tool will be changed to a certain extent. Therefore, when the calculation prediction based on the cutoff distance data shows that the processing tool will deviate from the required processing point at the final moving distance, the present invention analyzes the causes of the deviation including the factor of friction resistance based on the friction function, and formulates an emergency management plan, thereby improving the efficiency of analyzing and solving the causes of the deviation.
[0115] To summarize, the present invention utilizes deep learning analysis technology to obtain the axis coordinate data of the processing tool in different original positions and the coordinate data of the processing point required on the workpiece to be processed within a preset time, and calculates the distance between the two coordinate data. At the same time, the movement distance of the processing tool is collected within the preset time, and it is calculated to determine whether the processing tool will cause position deviation when it reaches the required processing point within this time. Moreover, within the preset time, the movement distance data of the processing tool up to the truncation time can be cut off. Therefore, if necessary, it can be calculated and predicted as early as possible whether the processing tool will cause position deviation when it reaches the required processing point from its original position. This is beneficial to improving operating efficiency and helping enterprises save production time costs. At the same time, when it is calculated and predicted that position deviation will occur, the causes of the position deviation, including the factor of friction resistance, can be analyzed, and an emergency management plan can be formulated, thereby further enabling the processing operations to proceed in an orderly manner and improving operating efficiency.
[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should be included in the scope of the claims of the present invention.
Claims
1. An intelligent control system for a high-precision CNC machine tool, characterized in that: include: A visual information acquisition module, used to acquire real-time on-site visual information provided by a preset CNC machine tool, wherein the visual information includes the size of a tool holder of the preset CNC machine tool, the perimeter of a workpiece to be processed, and the original distance data between the processing tool and the workpiece to be processed, and the visual information acquisition module includes a CCD camera; An image data processing module, the image data processing module comprising an image data compression module for compressing and processing the image data of the CCD camera, and an image interception module for intercepting image data of a preselected area in the image data compression module; A data fusion analysis unit, wherein the image data analysis unit includes a scanning module, a calculation module, a storage module and an analysis module; The scanning module is used to scan the flatness of the workpiece to be processed in real time on site, and the flatness to be scanned includes the flatness data of the upper and lower end surfaces of the workpiece to be processed; The calculation module calculates the flatness difference of the workpiece to be processed based on the flatness data scanned and acquired by the scanning module; The storage module is used to store the flatness difference data calculated by the calculation module and build a cloud database; The analysis module is used to analyze the distance between the edge point of the machining dimension and the nearest flatness difference based on the center point of the workpiece to be machined; An axis coordinate acquisition module is used to acquire the distance between the machining tool and the machining point of the workpiece to be machined at different orientations, wherein the distance is the horizontal coordinate distance, and preset the machining tool orientation data and the orientation data of the machining point to be machined, construct a three-dimensional horizontal distance model, and acquire the flatness difference data between different machining points and the nearest ones; A laser detection module, the laser detection module comprising a laser sensor for measuring the distance of laser oblique projection during the movement of the machining knife, an angle sensor for detecting the inclination angle value of the laser sensor, and an A / D conversion circuit for converting an analog signal of the laser sensor; The visual data capture module uses the previous position data of the processing tool as a base point to capture the distance moved by the processing tool to the point to be processed within a unit moving time, and obtains the spacing between the distance and the point to be processed based on the moving distance. At the same time, the moving distance within the unit moving time is divided to generate a prediction model.
2. The intelligent control system for a high-precision CNC machine tool according to claim 1, characterized in that: In the visual information acquisition module, the original distance data includes the height data of the machining tool and the workpiece to be processed and the orientation data of the machining tool based on the workpiece to be processed, and other required machining points are obtained based on the center point of the workpiece to be processed, and the machining points are arranged according to θ1, θ2, ..., θ n The time required for the machining tool to reach the preset machining point and the center point of the workpiece to be machined from the original position is calculated according to the following formula: Among them, T represents the unit movement time; Where, T k represents the moving time required for the machining tool to move to the kth machining point; C k represents the distance between the kth preset processing point and the coordinate trajectory of the processing tool, η represents the friction function during the movement of the processing tool, and η i represents the friction function collected during the i-th movement of the machining tool; On the basis of the above, the time required for the machining tool to move from the original position to the center point of the workpiece to be machined is calculated according to the following formula: Among them, T k represents the moving time required for moving to the kth processing point based on the processing tool; represents the coordinate trajectory distance between the center point of the workpiece to be processed and the processing tool obtained based on the perimeter data of the workpiece to be processed, δ i represents the original position data of the machining tool relative to the center point of the workpiece to be machined, measured for the i-th time before starting machining.
3. The intelligent control system for a high-precision CNC machine tool as claimed in claim 2, characterized in that: The friction functions of the machining tool during the movement are collected, and the sizes of the collected friction functions are divided into intervals of 2N / ㎡ to 5N / ㎡, 5N / ㎡ to 8N / ㎡, and 8N / ㎡ to 10N / ㎡. The distances moved by the machining tool to the center point of the workpiece to be processed and / or the preset machining point within the unit movement time under different interval friction functions are obtained, and calculated according to the following formula: Wherein, x represents the total unit movement time of the processing knife; In the formula, p i represents the i-th collected moving distance data based on the total unit moving time of the processing knife, j represents the cutoff distance data, and the cutoff distance data is cut off based on the moving distance data of the total unit moving time of the processing knife, x represents the preset moving distance under the total unit moving time minus the actual moving distance of the processing knife, d vi It represents the i-th collected moving time of the processing tool in the case of the v-th moving line trajectory.
4. The intelligent control system for a high-precision CNC machine tool as claimed in claim 3, characterized in that: The truncation distance data obtained based on the total unit movement time of the processing knife is divided into first truncation distance data, second truncation distance data and third truncation distance data in a step-by-step manner, and the first truncation distance data, the second truncation distance data and the third truncation distance data are all incremental data, and the distance data moved by the processing knife within the total unit movement time is obtained, and based on the distance data, combined with the total unit movement time, the average truncation distance data is calculated as follows: Among them, f k It represents the total moving distance of the machining tool collected during the total moving time of the kth unit; Where n is the time for collecting and / or intercepting the cutoff distance data, It represents the cutoff distance data obtained at the i-th collection and / or interception time, wherein a safety threshold is preset based on the minimum cutoff distance data. When the cutoff distance data of the processing knife movement in the future time period is less than the safety threshold, the system determines that it is in an abnormal state and issues an abnormal state alarm, otherwise, no determination is made.
5. The intelligent control system for a high-precision CNC machine tool as claimed in claim 4, characterized in that: A data pool is constructed for the collected and / or intercepted cutoff distance data below the safety threshold, and the data in the data pool is divided into several evaluation indicators through labeling, the evaluation indicator data in the data pool is counted, and the data is normalized to analyze the weight of each evaluation indicator data in the safety threshold.
6. The intelligent control system for a high-precision CNC machine tool according to claim 1, characterized in that: In the scanning module, it includes scanning the flatness next to the center point of the workpiece to be processed, specifically by pre-acquiring the diameter length data and / or circumference data of the center point after processing, and presetting a critical threshold based on the diameter length data and / or circumference data and the minimum safety distance at the uneven point. When the minimum safety distance scanned by the scanning module is lower than the critical threshold, the system determines that the processing operation is in an abnormal state and issues an abnormal state warning. Otherwise, no determination is made.
7. The intelligent control system for a high-precision CNC machine tool as claimed in claim 5, characterized in that: Based on the evaluation index data in the data pool, the processing tool movement friction data corresponding to the evaluation index data is obtained, and an early warning model is generated based on different friction data. Based on the early warning model, a hierarchical management plan corresponding to different levels of the evaluation index data is formulated through evidence-based and Delphi methods.
8. The intelligent control system for a high-precision CNC machine tool according to claim 1, characterized in that: In the analysis module, the distance between the edge point of the processed dimension and the nearest flatness difference is divided into Among them, n represents the nth flatness difference distance data, and a matching model is generated based on historical data of the same orientation and the same processing size. The matching model includes distance data corresponding to the minimum flatness difference of the edge point of the processing size. When the distance data corresponding to the minimum flatness difference of the edge point of the processing size with the center point in the future time period is greater than the distance data corresponding to the minimum flatness difference of the edge point of the processing size in the matching model, the system determines that the analysis result is abnormal, otherwise, it will not be determined.
9. The intelligent control system for a high-precision CNC machine tool according to claim 6, characterized in that: The scanning module also includes scanning the shape of the uneven points near the center point and / or the preset processing point of the workpiece to be processed, obtaining the scanned image data, and analyzing and comparing the scanned image data to obtain the point of the shape at the uneven point closest to the center point and / or the preset processing point, and analyzing and calculating whether the closest point is lower than the critical threshold. When the minimum safety distance scanned by the scanning module is lower than the critical threshold, the system determines that the processing operation is in an abnormal state and issues an abnormal state warning. Otherwise, no determination is made.
10. The method of intelligent control system for high-precision CNC machine tools according to claim 1, characterized in that: The following steps are involved: Acquire real-time on-site visual information provided by a preset CNC machine tool, including the preset CNC machine tool tool holder size, the perimeter of the workpiece to be processed, and the original distance data between the processing tool and the workpiece to be processed; Compressing the acquired visual information image data, and intercepting the preselected area image data in the compressed image data; Analyze the flatness of the workpiece to be processed in the acquired preselected area image data, calculate the flatness difference of the workpiece to be processed according to the acquired flatness data, and build a cloud database based on the acquired flatness difference data; Taking the center point of the workpiece to be processed as a reference, analyzing the distance between the edge point of the processing dimension and the nearest flatness difference; Obtaining the distance between the machining tool and the machining point of the workpiece to be machined at different orientations, presetting the machining tool orientation data and the orientation data of the machining point to be machined, constructing a three-dimensional lateral distance model, and simultaneously obtaining the flatness difference data of different machining points and the nearest ones; The positioning data of the processing tool at all times are used as a base point to intercept the distance moved by the processing tool to the processing point within a unit moving time, and the distance between the distance and the processing point is obtained based on the moving distance, and the moving distance within the unit moving time is divided to generate a prediction model; Based on the center point of the workpiece to be processed, other required processing points are obtained, the coordinate positions of the different processing points are obtained, the time required for the processing tool to move from the original position to the preset processing point and the center point of the workpiece to be processed is calculated, and the moving distance of the processing tool within the time range is obtained. The moving distance can be truncated and a safety threshold is preset. When the selected truncation distance data is less than the safety threshold, the system determines that it is in an abnormal state and issues an abnormal state alarm. Otherwise, no determination is made.
Citation Information
Patent Citations
Intelligent machine tool machining operation automatic identification control system based on machine vision
CN114425700A
Numerically-controlled machine tool intelligent tool setting system and method adopting machine vision
CN114800034A
Robot grinding track optimization method based on digital twinning and visual communication technology
CN116276328A
Numerical control machining product quality supervision system and method based on big data
CN117092963A
Laser processing method and system based on machine vision
CN118314138A
Cited By
Intelligent processing system based on artificial intelligence visual technology and control method thereof
CN119671231A
Multi-point milling path design method for full-surface feature structure of thin-wall spherical shell type micro component
CN120044882A
