Cutting path intelligent planning system for numerical control model cutting machine

Abstract

The application relates to the technical field of ant colony algorithm, in particular to a cutting path intelligent planning system for a numerical control model cutting machine, which comprises the following modules: a data acquisition module, which is used for acquiring the graph elements and thermal conductivity of a plate to be processed and acquiring the cutting speed and running power of the cutting machine; a path analysis module, which is used for calculating the thermal constraint characteristic value of each cutting graph element by comprehensively analyzing the geometric characteristics, curvature distribution, heat source intensity and thermal conduction effect of the graph elements; and a path planning module, which optimizes the heuristic information and volatility coefficient in the ant colony algorithm based on the constraint characteristic value, and determines the cutting path of the cutting machine on the plate to be processed based on all the graph elements on the plate to be processed by using the optimized ant colony algorithm. The application improves the cutting quality and precision by analyzing the influence of thermal deformation on the cutting path planning.

Description

Technical Field

[0001] This application relates to the field of ant colony algorithm technology, specifically to an intelligent cutting path planning system for CNC model cutting machines. Background Technology

[0002] In the field of CNC cutting, different cutting methods are used depending on the properties of the material being cut. In CNC cutting at steel foundries, thermal cutting is the most common method. Thermal cutting is a processing method that achieves separation by concentrating thermal energy to melt or burn the material. Taking laser cutting as an example, a high-energy-density laser beam is focused onto the surface of the workpiece, causing a localized area of ​​the workpiece to be instantly heated and melted, thus achieving the cutting process. It has advantages such as high precision and high efficiency, and is suitable for cutting various materials, making it widely used in high-precision cutting processes.

[0003] Using ant colony optimization (ACO) for intelligent laser cutting path planning ensures the cutting machine moves along an optimal trajectory, significantly reducing idle distance and thus saving processing time and improving cutting efficiency. Furthermore, path optimization reduces the movement distance and frequency of mechanical components, mitigating wear and reducing maintenance costs. However, traditional path planning typically focuses solely on path length and idle distance, neglecting the heat conduction effect during laser cutting. For high-precision, complex patterns, heat accumulation can easily lead to localized overheating, deformation, or even damage to the workpiece, severely impacting cutting quality and precision. Summary of the Invention

[0004] To address the aforementioned technical problems, the purpose of this application is to provide an intelligent cutting path planning system for CNC model cutting machines, and the specific technical solution adopted is as follows:

[0005] This application proposes an intelligent cutting path planning system for a CNC model cutting machine, the system comprising:

[0006] The data acquisition module is used to acquire the binary image and thermal conductivity of the board to be processed, extract all contours in the binary image and record them as primitives, and acquire the cutting speed and operating power of the cutting machine during the cutting process of the board to be processed.

[0007] The path analysis module is used to filter candidate positioning points for each graphic element from all pixels based on the curvature of all pixels on each graphic element; determine the heat source intensity of the currently cut graphic element based on the contour length and area of ​​the currently cut graphic element, combined with the cutting speed and the operating power; and determine the thermal influence characteristic value of each graphic element to be cut based on the distance from all candidate positioning points of each graphic element to be cut to the centroid of the currently cut graphic element, combined with the thermal conductivity and the heat source intensity.

[0008] Based on the size characteristics of each graphic element to be cut, a first feature value is determined for each graphic element to be cut; based on the difference in curvature between all adjacent pixels on each graphic element to be cut and the dispersion of the curvature of all pixels, a second feature value is determined for each graphic element to be cut, and combined with the first feature value, a thermally sensitive feature value is determined for each graphic element to be cut; based on the thermally affected feature value and the thermally sensitive feature value, a thermally constrained feature value is determined for each graphic element to be cut.

[0009] The path planning module optimizes the heuristic information and volatility coefficient in the ant colony algorithm based on the constraint feature values. Based on all primitives on the board to be processed, the optimized ant colony algorithm is used to determine the cutting path of the cutting machine on the board to be processed.

[0010] Preferably, the candidate positioning points of each graphic element are the first preset number of pixels with curvature in the descending order of curvature of all pixels on each graphic element.

[0011] Preferably, the method for determining the heat source intensity of the currently cut graphic element is as follows:

[0012] Calculate the ratio of the outline length of the currently cut element to the cutting speed, and record it as the cutting time of the currently cut element;

[0013] The cutting time and the operating power of the cutting head are both positively correlated with the heat source intensity of the current cut element, while the area of ​​the current cut element is negatively correlated with the heat source intensity of the current cut element.

[0014] Preferably, the method for determining the thermal influence characteristic values ​​of each graphic element to be cut is as follows:

[0015] Calculate the inverse exponential result of the distance from each candidate pixel on each primitive to be cut to the current primitive to be cut, and take the average of the exponential results of all candidate pixels as the heat feature value of each primitive to be cut.

[0016] The product of the thermal characteristic value of each element to be cut, the heat source intensity of the element currently being cut, and the thermal conductivity of the material to be processed is used as the thermal influence characteristic value of each element to be cut.

[0017] Preferably, the first characteristic value of each graphic element to be cut is the absolute difference between the length and width of the smallest bounding rectangle of each graphic element to be cut.

[0018] Preferably, the second feature value of each pixel to be cut is the result of multiplying the mean of the curvature difference between all adjacent pixels on each pixel by the curvature dispersion of all pixels.

[0019] Preferably, the expression for the thermally sensitive feature value of each graphic element to be cut is: In the formula, This represents the thermally sensitive feature value of the primitive m to be cut; , Let represent the first eigenvalue and the second eigenvalue of the primitive m to be cut, respectively; , These represent the preset first weight and the preset second weight, respectively. ; exp() represents an exponential function with the natural constant as the base.

[0020] Preferably, the thermal constraint characteristic value of each graphic element to be cut is the normalized value of the result of multiplying the thermal influence characteristic value and the thermal sensitivity characteristic value of each cut graphic element.

[0021] Preferably, the heuristic information and volatility coefficient in the optimized ant colony algorithm include:

[0022] Heuristics between the currently cut primitive and the primitive m to be cut The expression is: In the formula, This represents the distance between the primitive m to be cut and the primitive currently being cut; This represents the thermal constraint characteristic value of the primitive m to be cut; , These represent the preset first weight factor and the preset second weight factor, respectively. ;

[0023] Volatility between the currently cut primitive and the primitive m to be cut The expression is: ; This represents the thermal constraint characteristic value of the primitive m to be cut; This indicates the preset volatility coefficient; exp() represents an exponential function with the natural constant as the base.

[0024] The heuristic degree and the volatility degree are used as the heuristic information and volatility coefficient in the ant colony algorithm, respectively.

[0025] Preferably, the method for determining the cutting path of the material to be processed by the cutting machine is as follows:

[0026] The algorithm takes all primitives in the material to be processed as input to the optimized ant colony algorithm, where the primitive closest to the initial position of the cutting head is taken as the initial primitive to be cut, and outputs the optimal cutting path for the material to be processed.

[0027] This application has the following beneficial effects:

[0028] This application constructs thermal influence feature values ​​by comprehensively considering the geometric features, heat source intensity, and heat conduction effect of graphic elements to improve the heuristic information of the ant colony algorithm. This allows for dynamic avoidance of thermal deformation risks during cutting path planning, thereby improving the cutting quality and accuracy of high-density complex patterns. Furthermore, this application constructs thermally sensitive feature values ​​by comprehensively analyzing the size characteristics and contour complexity of the graphic elements to be cut. These feature values ​​are then combined with the thermal influence feature values ​​to form thermal constraint feature values, which are used to assess the risk of thermal deformation during cutting, thereby optimizing the cutting path selection and improving cutting quality and accuracy. In addition, this embodiment optimizes the heuristic information and volatility coefficient of the ant colony algorithm based on the thermal constraint feature values, realizing intelligent planning of the cutting path, effectively avoiding local deformation caused by heat accumulation, and significantly improving the cutting quality and accuracy of complex patterns. Attached Figure Description

[0029] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is a block diagram of an intelligent cutting path planning system for a CNC model cutting machine provided in one embodiment of this application;

[0031] Figure 2 A flowchart illustrating the process of obtaining thermal constraint feature values ​​according to an embodiment of this application. Detailed Implementation

[0032] To further illustrate the technical means and effects adopted by this application to achieve the intended inventive purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of the intelligent cutting path planning system for a CNC model cutting machine proposed in this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0033] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0034] The following description, in conjunction with the accompanying drawings, details the specific scheme of the intelligent cutting path planning system for CNC model cutting machines provided in this application.

[0035] Please see Figure 1The diagram illustrates a block diagram of an intelligent cutting path planning system for a CNC model cutting machine according to an embodiment of this application. The system includes: a data acquisition module 101, a path analysis module 102, and a path planning module 103.

[0036] The data acquisition module 101 is used to acquire the binary image and thermal conductivity of the plate to be processed, extract all contours in the binary image and record them as primitives, and acquire the cutting speed and operating power of the cutting machine during the cutting process of the plate to be processed.

[0037] The binary image and thermal conductivity of the electronic design drawing of the board to be processed are obtained from the industrial processing software. All contours in the binary image are extracted using a contour extraction algorithm and recorded as primitives. Furthermore, the cutting speed and operating power of the cutting head during the cutting process of the board to be processed are obtained from the industrial processing software. The cutting speed and operating power are different for different cutting shapes, that is, the cutting speed and operating power will change. However, for each primitive, the cutting speed and operating power of the cutting head are usually uniform. The cutting speed and operating power of the cutting head will change due to the shape of different primitives.

[0038] It should be noted that there are many commonly used contour extraction algorithms. In this embodiment, the erosion algorithm in morphological operations is used to obtain all contours in the binary image. In practical applications, as other implementation methods, implementers may also use other contour algorithms such as threshold segmentation methods according to specific circumstances. This embodiment does not impose any special restrictions.

[0039] Among them, the erosion algorithm in morphological operations is a well-known technique, and the specific process of using it to extract contours from binary images will not be elaborated here.

[0040] In this system, a two-dimensional coordinate system is constructed with the position of the cutting head when it is in standby mode as the origin O and the binary image of the material to be cut as the plane, which facilitates the subsequent analysis of the graphic elements.

[0041] To eliminate the influence of data dimensions on subsequent calculations, the cutting speed, operating power, and thermal conductivity are normalized respectively. In this embodiment, the maximum-minimum normalization method is used to normalize the above three types of data respectively. In practical applications, implementers may also choose other normalization methods such as z-score normalization according to specific circumstances. This embodiment does not impose any special restrictions on the selection of normalization methods.

[0042] Among them, the maximum-minimum normalization method is a well-known technique, and the specific process of using it to normalize data will not be elaborated here.

[0043] The path analysis module 102 is used to calculate the thermal constraint characteristic value of each graphic element to be cut by comprehensively analyzing the geometric features, curvature distribution, heat source intensity and heat conduction effect of the graphic elements.

[0044] Throughout the cutting process, it is assumed that there are a total of [number] elements in the image to be processed. Each primitive is represented as primitive A positioning point is determined on each outline. This refers to the drilling point of the cutting head on the outline of the graphic element. Since drilling affects cutting efficiency and is costly, the principle of minimizing drilling should be followed, with each graphic element having exactly one drilling point. Therefore, the total travel distance of the cutting head is the distance from the origin... Start from the first primitive positioning point The distance, the outline length of all primitives, the space distance between all primitives, and the last primitive The sum of the distances from the positioning points to the origin, and the fact that the outline length of all primitives remains constant, means that the optimal cutting path is the distance the cutting head travels from the origin, traversing all primitive positioning points, and returning to the origin. Therefore, the cutting path planning can be represented as a Traveling Salesman Problem (TSP), and its optimization objective can be expressed as:

[0045]

[0046] In the formula, Indicates the location point of the first graphic element. To the origin The distance; Represents the location point of the optimal primitive. To the origin The distance; Indicates the first The positioning point of each graphic element With the The positioning point of each graphic element The distance between them represents the distance traveled between the two primitives. Under this optimization objective function, the selection of the positioning points and the cutting order of the primitives are the determining factors for the optimal cutting path.

[0047] However, when ant colony optimization plans and optimizes cutting paths, it usually takes the length of the idle path as the optimization target. In actual processing, the heat conduction effect of heat accumulation is an important influencing factor in the thermal cutting process. For high-precision complex patterns, such as patterns where the distance between each element is very close and the distribution density is high, traditional cutting path planning does not consider the heat conduction effect of the material, which leads to local overheating of the plate, causing deformation or even damage to the plate, thus affecting the cutting quality and accuracy. In this case, the cutting path planned by ant colony algorithm is difficult to meet production requirements.

[0048] To address the aforementioned issues, this embodiment considers the heat conduction effect during plate cutting and the geometric features of the primitives to construct thermal effect feature values ​​and heat sensitivity feature values ​​for the primitives. Then, based on these two factors, thermal constraint feature values ​​for the primitives are constructed to improve the optimization process of the ant colony algorithm. Under the constraint of the thermal constraint feature values, the optimal cutting path and cutting effect are guaranteed. The flowchart of the thermal constraint feature value acquisition process provided in this embodiment is shown below. Figure 2 As shown, the specific construction process of thermal constraint eigenvalues ​​is as follows:

[0049] S1: Based on the curvature of all pixels on each graphic element, candidate positioning points for each graphic element are selected from all pixels; based on the contour length and area of ​​the currently cut graphic element, and combined with the cutting speed and the operating power, the heat source intensity of the currently cut graphic element is determined; based on the distance from all candidate positioning points of each graphic element to be cut to the centroid of the currently cut graphic element, and combined with the thermal conductivity and the heat source intensity, the thermal influence characteristic value of each graphic element to be cut is determined.

[0050] The first step is the selection of positioning points. In this embodiment, based on the curvature of all pixels on each primitive, candidate positioning points for each primitive are selected from all pixels. Specifically:

[0051] In this embodiment, the pixels corresponding to the first preset number of curvatures in the descending order of curvature of all pixels on each graphic element are used as candidate positioning points for each graphic element. The preset number is set manually. In this embodiment, the preset number is 10. In actual applications, as other implementation methods, implementers can also set it according to specific circumstances. This embodiment does not impose any special restrictions.

[0052] The method for calculating curvature is a well-known technique, and its specific calculation process will not be elaborated here.

[0053] Furthermore, in this embodiment, based on the outline length and area of ​​the currently cut graphic element, and in conjunction with the cutting speed and the operating power, the heat source intensity of the currently cut graphic element is determined, specifically as follows:

[0054] In this embodiment, the ratio of the outline length of the currently cut graphic element to the cutting speed is calculated and recorded as the cutting time of the currently cut graphic element;

[0055] The cutting time and the operating power of the cutting head are both positively correlated with the heat source intensity of the current cut element, while the area of ​​the current cut element is negatively correlated with the heat source intensity of the current cut element.

[0056] It should be understood that a positive correlation means that the dependent variable increases as the independent variable increases, and the dependent variable decreases as the independent variable decreases. The specific relationship can be additive or multiplicative, etc., and is determined by the actual application. This application does not impose any special restrictions. A negative correlation means that the dependent variable decreases as the independent variable increases, and the dependent variable increases as the independent variable decreases. The relationship can be subtractive or divisive, etc., and is determined by the actual application.

[0057] Preferably, in this embodiment, the expression for the heat source intensity Q of the currently cut primitive is: In the formula, Indicates the cutting time of the currently cut element; Indicates the operating power of the cutting head; This represents the area of ​​the currently cut primitive; exp() represents an exponential function with the natural constant as the base; in practical applications, as other implementation methods, implementers may also use other positive and negative correlation representations for calculation according to specific circumstances, and this embodiment does not impose any special restrictions.

[0058] It should be noted that, in order to eliminate the influence of dimensions, the areas mentioned above are all values ​​after normalization. In this embodiment, the normalization method used is the maximum-minimum normalization method. In practical applications, as other implementation methods, implementers may also use other normalization methods such as z-score standardization according to specific circumstances. This embodiment does not impose any special restrictions on the selection of normalization methods.

[0059] Based on the heat source intensity of the currently cut element, it can be understood that the heat source intensity reflects the degree of heat accumulation generated by a element on the surrounding material during the cutting process. The longer the cutting time, the longer the continuous heat input time, resulting in more severe heat accumulation. The surrounding material is more likely to overheat, leading to an increased risk of deformation. Therefore, the corresponding heat source intensity is also relatively large. At the same time, if the operating power of the cutting head is greater, it means that more heat is input per unit time, resulting in a greater heat source intensity, which can easily lead to local overheating. Therefore, the corresponding heat source intensity is also relatively large. In addition, if the area of ​​the currently cut element is smaller, it means that the heat distribution is more concentrated, the heat source intensity is greater, the heat accumulation is more severe, and the risk of deformation is higher.

[0060] Conversely, the shorter the cutting time, the shorter the continuous heat input time, the less heat accumulation, the less likely the surrounding material is to overheat, and the lower the risk of deformation. Therefore, the corresponding heat source intensity is also relatively small. At the same time, if the operating power of the cutting head is smaller, less heat is input per unit time, the heat source intensity is smaller, and the risk of local overheating is reduced. Therefore, the corresponding heat source intensity is also relatively small. In addition, if the area of ​​the currently cut element is larger, the heat distribution is more uniform, the heat source intensity is smaller, the heat accumulation is less, and the risk of deformation is also lower.

[0061] Furthermore, in this embodiment, based on the distances from all candidate positioning points of each graphic element to be cut to the centroid of the current graphic element to be cut, and in conjunction with the thermal conductivity and the heat source intensity, the thermal influence characteristic value of each graphic element to be cut is determined, specifically as follows:

[0062] In this embodiment, the inverse exponentialized result of the distance from each candidate pixel on each primitive to be cut to the current primitive to be cut is calculated, and the average of the exponentialized results of all candidate pixels is taken as the heat feature value of each primitive to be cut.

[0063] The product of the thermal characteristic value of each element to be cut, the heat source intensity of the element currently being cut, and the thermal conductivity of the material to be processed is used as the thermal influence characteristic value of each element to be cut.

[0064] The method for obtaining the centroid is a well-known technique, and the specific acquisition process will not be described in detail here.

[0065] It should be further explained that, in this embodiment, the so-called exponentialization result is the result of exponentializing the distance from each candidate pixel on each to-be-cut primitive to the current to-be-cut primitive, with the natural constant as the base and the inverse of the distance from each candidate pixel on each to-be-cut primitive to the current to-be-cut primitive as the independent variable. In practical applications, as other implementation methods, implementers may also adopt logically consistent exponential functions according to specific circumstances. This embodiment does not impose any special restrictions.

[0066] Based on the thermal impact characteristic values ​​of each element to be cut, it can be understood that the thermal impact characteristic value represents the average degree of thermal impact of the element currently being cut on the element to be cut. If the thermal conductivity of the material to be cut is greater, it means that the material to be cut has good thermal conductivity and heat is easily transferred. Therefore, the element to be cut is more affected by heat and has a higher risk of deformation. Thus, the corresponding thermal impact characteristic value is larger. At the same time, if the heat source intensity of the element to be cut is greater and the distance between the element to be cut and the element to be cut is closer, it means that the heat input is greater when the element to be cut is cut, resulting in a greater thermal impact on the element to be cut. The corresponding thermal impact characteristic value is larger.

[0067] Conversely, the lower the thermal conductivity of the material to be cut, the worse the thermal conductivity of the material, and the less easily heat is transferred. Therefore, the element to be cut is less affected by heat, and the risk of deformation is reduced. Thus, the corresponding thermal influence characteristic value is smaller. At the same time, the lower the heat source intensity of the element to be cut and the greater the distance between the element to be cut and the element to be cut, the smaller the heat input when the element to be cut is cut. This results in the element to be cut being less affected by heat, and the corresponding thermal influence characteristic value is smaller.

[0068] Thus, this embodiment constructs thermal influence feature values ​​by comprehensively considering the geometric features of primitives, heat source intensity, and heat conduction effect, in order to improve the heuristic information of the ant colony algorithm, thereby dynamically avoiding the risk of thermal deformation in cutting path planning and improving the cutting quality and accuracy of high-density complex patterns.

[0069] S2: Based on the size characteristics of each graphic element to be cut, determine the first feature value of each graphic element to be cut; based on the difference in curvature between all adjacent pixels on each graphic element to be cut and the dispersion of the curvature of all pixels, determine the second feature value of each graphic element to be cut, and combine the first feature value to determine the thermally sensitive feature value of each graphic element to be cut; based on the thermally affected feature value and the thermally sensitive feature value, determine the thermally constrained feature value of each graphic element to be cut.

[0070] Different geometric shapes of primitives respond differently to thermal effects during the cutting process. For example, serrated or slender structures, according to the Gaussian heat source model, will have a thermal effect on the surrounding area from the heat source field centered on the cutting head during cutting. Serrated or slender primitives are cut continuously in a short time under the influence of the heat source field, making them more prone to local deformation due to heat accumulation, which affects the cutting accuracy.

[0071] Therefore, based on the above analysis, this embodiment determines the first feature value of each graphic element to be cut based on its dimensional characteristics, which is used to characterize the elongation of the graphic element to be cut, specifically as follows:

[0072] In this embodiment, the absolute difference between the length and width of the minimum bounding rectangle of each graphic element to be cut is taken as the first feature value of each graphic element to be cut. If the first feature value of the current graphic element to be cut is larger, it indicates that the current graphic element to be cut is more slender. Slender structures are more prone to deformation due to uneven thermal stress when heated, and have high sensitivity. Conversely, if the first feature value of the current graphic element to be cut is smaller, it indicates that the current graphic element to be cut has a symmetrical structure, uniform thermal stress distribution, and low sensitivity.

[0073] Furthermore, in this embodiment, based on the difference in curvature between all adjacent pixels on each primitive to be cut and the dispersion of the curvature of all pixels, a second feature value is determined for characterization, specifically as follows:

[0074] In this embodiment, the mean of the curvature difference between all adjacent pixels on each primitive to be cut is multiplied by the curvature dispersion of all pixels, and the result is used as the second feature value of each primitive to be cut.

[0075] It should be noted that there are many methods to measure the degree of data dispersion. In this embodiment, the variance of the curvature of all pixels on each primitive to be cut is taken as the degree of dispersion of the curvature of all pixels on each primitive to be cut. In practical applications, as other implementation methods, implementers may also use other methods such as standard deviation or coefficient of variation to measure the degree of data dispersion in combination with specific circumstances. This embodiment does not impose any special restrictions on the selection of methods for measuring the degree of data dispersion.

[0076] Based on the second eigenvalue of each primitive to be cut, it can be understood that the second eigenvalue reflects the complexity of the primitive's outline and is used to characterize whether the primitive's outline is prone to thermal stress concentration due to sudden changes in local curvature when heated. If the difference in curvature between all adjacent pixels on the primitive to be cut is greater, it indicates that the primitive's outline changes drastically, indicating that the primitive is highly thermally sensitive. Therefore, the corresponding second eigenvalue is correspondingly larger. At the same time, if the dispersion of curvature of all pixels on the primitive to be cut is greater, it indicates that the primitive's outline is complex and its thermal sensitivity is higher. Therefore, the corresponding second eigenvalue is correspondingly larger.

[0077] Conversely, if the curvature difference between all adjacent pixels on the primitive to be cut is smaller, it indicates that the contour of the primitive to be cut changes gently, indicating that the thermal sensitivity of the primitive to be cut is low. Therefore, the corresponding second feature value is relatively small. At the same time, if the dispersion of the curvature of all pixels on the primitive to be cut is smaller, it indicates that the contour of the primitive to be cut is simple and the thermal sensitivity is lower. Therefore, the corresponding second feature value is relatively small.

[0078] Furthermore, in this embodiment, based on the first feature value and the second feature value, the heat-sensitive feature value of each graphic element to be cut is determined, specifically as follows:

[0079] As one implementation method, in this embodiment, the thermally sensitive feature value of the primitive m to be cut is... The expression is: In the formula, , Let represent the first eigenvalue and the second eigenvalue of the primitive m to be cut, respectively; , These represent the preset first weight and the preset second weight, respectively. ; exp() represents an exponential function with the natural constant as the base.

[0080] It should be noted that the values ​​of the preset first weight and the preset second weight are both set manually. In this embodiment, the preset first weight is set to 0.5 and the preset second weight is set to 0.5. In actual applications, as other implementation methods, implementers can also set them according to specific circumstances. This embodiment does not impose any special restrictions.

[0081] Based on the thermal sensitivity feature values ​​of each graphic element to be cut, it can be understood that the thermal sensitivity feature value combines the elongation and contour complexity of the graphic element to be cut, and is used to evaluate the sensitivity of the graphic element to thermal deformation. The larger the thermal sensitivity feature value, the easier it is for the graphic element to be cut to deform when heated. If the first feature value of the graphic element to be cut is larger, it means that the graphic element to be cut is more elongated and has a higher thermal sensitivity, and the corresponding thermal sensitivity feature value is larger. At the same time, if the second feature value of the graphic element to be cut is larger, it means that the contour of the graphic element to be cut is more complex and has a higher thermal sensitivity, and the corresponding thermal sensitivity feature value is larger.

[0082] Conversely, the smaller the first feature value of the primitive to be cut, the less elongated the primitive is, the lower its thermal sensitivity, and the smaller the corresponding thermal sensitivity feature value. At the same time, the smaller the second feature value of the primitive to be cut, the simpler its outline is, the lower its thermal sensitivity, and the smaller the corresponding thermal sensitivity feature value.

[0083] In summary, this embodiment determines the thermal constraint feature value of each graphic element to be cut based on its thermal influence feature value and thermal sensitivity feature value. Specifically, in this embodiment, the normalized value of the result of multiplying the thermal influence feature value and thermal sensitivity feature value of each graphic element to be cut is used as the thermal constraint feature value of each graphic element to be cut.

[0084] Based on the thermal constraint characteristic values ​​of each graphic element to be cut, it can be understood that the thermal constraint characteristic value is a comprehensive index of the thermal influence characteristic value and the thermal sensitivity characteristic value. It is used to determine whether there is a risk of thermal deformation if a certain graphic element to be cut is cut next. The larger the thermal constraint characteristic value, the less suitable the graphic element to be cut is for immediate cutting. If the thermal influence characteristic value of the graphic element to be cut is larger, it means that the graphic element to be cut is greatly affected by heat and the cutting risk is high. Therefore, the corresponding thermal constraint characteristic value is larger. At the same time, if the thermal sensitivity characteristic value of the graphic element to be cut is larger, it means that the thermal sensitivity of the graphic element to be cut is higher and the risk of cutting the graphic element to be cut is higher. Therefore, the corresponding thermal constraint characteristic value is larger.

[0085] Conversely, the smaller the thermal impact characteristic value of the element to be cut, the smaller the thermal impact and the lower the cutting risk. Therefore, the smaller the corresponding thermal constraint characteristic value. At the same time, the smaller the thermal sensitivity characteristic value of the element to be cut, the lower the thermal sensitivity and the lower the risk of cutting the element. Therefore, the smaller the corresponding thermal constraint characteristic value.

[0086] Thus, this embodiment constructs thermally sensitive feature values ​​by comprehensively analyzing the dimensional characteristics and contour complexity of the graphic elements to be cut, and combines them with thermally affected feature values ​​to form thermally constrained feature values, which are used to assess the risk of thermal deformation during the cutting process, thereby optimizing the selection of the cutting path and improving processing accuracy and stability.

[0087] The path planning module 103 optimizes the heuristic information and volatility coefficient in the ant colony algorithm based on the constraint feature values, and uses the optimized ant colony algorithm to determine the cutting path of the cutting machine for the plate to be processed based on all primitives on the plate to be processed.

[0088] During the cutting process, the thermal constraint feature value, the heuristic information and volatility coefficient in the ant colony algorithm are optimized to plan the optimal cutting path using the optimized ant colony algorithm. The specific process is as follows:

[0089] The heuristic information in the traditional ant colony algorithm is defined as the reciprocal of the path length. However, considering the influence of heat conduction between primitives during the cutting process, this embodiment optimizes the heuristic information based on the distance between the currently cut primitive and each primitive to be cut, as well as the thermal constraint feature value. Specifically:

[0090] As one implementation method, in this embodiment, firstly, all primitives in the board to be cut are used as input to the ant colony algorithm. The primitive closest to the initial position of the cutting head is used as the initial primitive to be cut in the ant colony algorithm. The number of ants is set to 100, the initial amount of pheromone is set to 0.1, and the maximum number of iterations is set to 100. In actual practice, the implementer can also set the number of ants, the initial amount of pheromone, and the number of iterations according to the specific situation. This embodiment does not impose any special restrictions.

[0091] Furthermore, based on the distance between the currently cut primitive and each primitive to be cut, and the thermal constraint feature value, the heuristic information is optimized. Specifically, the heuristic degree between the currently cut primitive and the primitive to be cut m is optimized. The expression is: In the formula, This represents the distance between the primitive m to be cut and the primitive currently being cut; This represents the thermal constraint characteristic value of the primitive m to be cut; , These represent the preset first weight factor and the preset second weight factor, respectively. .

[0092] Traverse all primitives in the material to be cut, obtain the heuristic degree between any two primitives, and use the heuristic degree as the heuristic information in the traditional ant colony algorithm.

[0093] It should be noted that the values ​​of the preset first weight factor and the preset second weight factor are both set manually. In this embodiment, the value of the preset first weight factor is 0.7 and the value of the preset second weight factor is 0.3. In actual application, as other implementation methods, implementers can also set them according to specific circumstances. This embodiment does not impose any special restrictions.

[0094] It should be noted that, in this embodiment, when calculating the distance between the graphic element m to be cut and the currently cut graphic element, the minimum value among the distances between all candidate positioning points of the graphic element m to be cut and all candidate positioning points of the currently cut graphic element is taken as the distance between the graphic element m to be cut and the currently cut graphic element.

[0095] Based on the optimized heuristic information, it can be understood that by introducing thermal constraint feature values ​​to improve the heuristic information of the ant colony algorithm, unlike traditional heuristic information which only relies on the spatial distance between primitives, the improved heuristic comprehensively considers the influence of thermal conduction and the sensitivity of primitives to thermal deformation. Specifically, the larger the value of the thermal constraint feature value, the stronger the thermal conduction influence of the primitive to be cut on the primitive to be cut, and the higher its risk of thermal deformation. At this time, the value of the heuristic information is reduced accordingly, thereby reducing the probability that the primitive to be cut is selected as the next cutting target. This realizes dynamic avoidance of high thermal deformation risk areas in the cutting path planning and effectively reduces the cutting error risk caused by thermal deformation. Conversely, if the value of the thermal constraint feature value is smaller, it indicates that the thermal deformation risk of the primitive to be cut as the next cutting target is lower, and the value of the heuristic information is larger, and the probability that it is selected as the next cutting target is also increased.

[0096] Furthermore, based on the aforementioned thermal constraint characteristic value, the volatility coefficient is optimized, specifically as follows:

[0097] In this embodiment, the volatility between the currently cut primitive and the primitive m to be cut is... The expression is: ; This represents the thermal constraint characteristic value of the primitive m to be cut; represents the preset volatility coefficient; exp() represents an exponential function with the natural constant as the base.

[0098] It should be noted that the preset volatility coefficient is set manually. In this embodiment, the preset volatility coefficient is set to 0.5. In actual applications, as other implementation methods, implementers can also set it according to specific circumstances. This embodiment does not impose any special restrictions.

[0099] Furthermore, by traversing all primitives in the material to be cut, the volatility between any two primitives is obtained, and the heuristic is used as the volatility coefficient in the traditional ant colony algorithm.

[0100] Based on the optimized volatility coefficient, it can be understood that the advantage of this design is that when ants visit different primitives, they can dynamically adjust the decay rate of pheromones according to the thermal constraint feature value of the primitive to be cut. When the thermal constraint feature value of the primitive to be cut is high, it indicates that the primitive to be cut is in a high heat-affected area. At this time, the pheromone volatilization rate is accelerated, reducing the accumulation of pheromones, thereby guiding the algorithm to automatically avoid continuous high heat-affected paths and effectively reducing the risk of thermal deformation. Conversely, when the thermal constraint feature value is small, the pheromone retention rate is high, which can enhance the exploration of safe paths and accelerate the convergence speed of the algorithm.

[0101] Finally, after optimizing the heuristic information and volatility coefficient in the ant colony algorithm, the optimal cutting path for the board to be processed is output.

[0102] Thus, this embodiment comprehensively evaluates the risk of thermal deformation of primitives during the cutting process by constructing thermally affected feature values ​​and thermally sensitive feature values. Based on this, it optimizes the heuristic information and volatility coefficient of the ant colony algorithm to achieve intelligent planning of the cutting path, effectively avoids local deformation caused by heat accumulation, and significantly improves the cutting accuracy and processing stability of complex patterns.

[0103] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0104] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0105] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.

Claims

1. An intelligent cutting path planning system for CNC model cutting machines, characterized in that, The system includes: The data acquisition module is used to acquire the binary image and thermal conductivity of the board to be processed, extract all contours in the binary image and record them as primitives, and acquire the cutting speed and operating power of the cutting machine during the cutting process of the board to be processed. The path analysis module is used to filter candidate positioning points for each graphic element from all pixels based on the curvature of all pixels on each graphic element; determine the heat source intensity of the currently cut graphic element based on the contour length and area of ​​the currently cut graphic element, combined with the cutting speed and the operating power; and determine the thermal influence characteristic value of each graphic element to be cut based on the distance from all candidate positioning points of each graphic element to be cut to the centroid of the currently cut graphic element, combined with the thermal conductivity and the heat source intensity. Based on the size characteristics of each graphic element to be cut, a first feature value is determined for each graphic element to be cut; based on the difference in curvature between all adjacent pixels on each graphic element to be cut and the dispersion of the curvature of all pixels, a second feature value is determined for each graphic element to be cut, and combined with the first feature value, a thermally sensitive feature value is determined for each graphic element to be cut; based on the thermally affected feature value and the thermally sensitive feature value, a thermally constrained feature value is determined for each graphic element to be cut. The path planning module optimizes the heuristic information and volatility coefficient in the ant colony algorithm based on the constraint feature values. Based on all primitives on the board to be processed, the optimized ant colony algorithm is used to determine the cutting path of the cutting machine for the board to be processed. The first characteristic value of each graphic element to be cut is the absolute difference between the length and width of the minimum bounding rectangle of each graphic element to be cut; The second feature value of each primitive to be cut is the result of multiplying the mean of the curvature difference between all adjacent pixels on each primitive to be cut by the degree of curvature dispersion of all pixels. The heuristic information and volatility coefficient in the optimized ant colony algorithm include: Heuristics between the currently cut primitive and the primitive m to be cut The expression is: In the formula, This represents the distance between the primitive m to be cut and the primitive currently being cut; This represents the thermal constraint characteristic value of the primitive m to be cut; , These represent the preset first weighting factor and the preset second weighting factor, respectively. ; Volatility between the currently cut primitive and the primitive m to be cut The expression is: ; This indicates the preset volatility coefficient; exp() represents an exponential function with the natural constant as the base. The heuristic degree and the volatility degree are used as the heuristic information and volatility coefficient in the ant colony algorithm, respectively.

2. The intelligent cutting path planning system for a CNC model cutting machine according to claim 1, characterized in that, The candidate positioning points for each graphic element are the pixels corresponding to the first preset number of curvatures in the descending order of curvature of all pixels on each graphic element.

3. The intelligent cutting path planning system for a CNC model cutting machine according to claim 1, characterized in that, The method for determining the heat source intensity of the currently cut graphic element is as follows: Calculate the ratio of the outline length of the currently cut element to the cutting speed, and record it as the cutting time of the currently cut element; The product of the cutting time of the current cut element, the negative exponential function value of the cut element, and the operating power of the cutting head is used as the heat source intensity of the current cut element.

4. The intelligent cutting path planning system for a CNC model cutting machine according to claim 1, characterized in that, The method for determining the thermal influence characteristic values ​​of each graphic element to be cut is as follows: Calculate the reciprocal of the distance from each candidate pixel on each primitive to be cut to the current primitive to be cut, and obtain its exponentialized result. Take the average of the exponentialized results of all candidate pixels and record it as the heat feature value of each primitive to be cut. The product of the thermal characteristic value of each element to be cut, the heat source intensity of the element currently being cut, and the thermal conductivity of the material to be processed is used as the thermal influence characteristic value of each element to be cut.

5. The intelligent cutting path planning system for a CNC model cutting machine according to claim 1, characterized in that, The expression for the thermally sensitive feature value of each graphic element to be cut is: In the formula, This represents the thermally sensitive feature value of the primitive m to be cut; , Let represent the first and second eigenvalues ​​of the primitive m to be cut, respectively; , These represent the preset first weight and the preset second weight, respectively. ; exp() represents an exponential function with the natural constant as the base.

6. The intelligent cutting path planning system for a CNC model cutting machine according to claim 1, characterized in that, The thermal constraint feature value of each element to be cut is the normalized value of the result of multiplying the thermal influence feature value and the thermal sensitivity feature value of each element to be cut.

7. The intelligent cutting path planning system for a CNC model cutting machine according to claim 1, characterized in that, The method for determining the cutting path of the cutting machine on the sheet material to be processed is as follows: The algorithm takes all primitives in the material to be processed as input to the optimized ant colony algorithm, where the primitive closest to the initial position of the cutting head is taken as the initial primitive to be cut, and outputs the optimal cutting path for the material to be processed.

Images