A multi-point collaborative optimization insulation board cutting method and device

Abstract

The present application provides a multi-point collaboratively optimized insulation board cutting method and device, which relates to the technical field of substrate cutting. The method includes: constructing a component characteristic information distribution, optimizing the cutting points, obtaining an optimal cutting point array, and then performing multi-point collaborative cutting optimization on the cutting parameters of multiple optimal cutting points to obtain a cutting parameter combination library with the smallest cutting specification deviation coefficient, obtaining a cutting line component characteristic information distribution by index detection, optimizing the cutting parameter combination within the cutting parameter combination library, and obtaining the optimal cutting parameter combination for cutting the insulation board substrate. The present application can solve the technical problem that the prior art lacks component detection of the insulation board substrate and optimization of the cutting point array, resulting in poor consistency of the composition of the insulation board after cutting, low dimensional accuracy, and further affecting the quality and performance of the insulation board. The cutting parameters can be optimized to reduce the impact of cutting on material properties, thereby improving the overall quality and performance of the insulation board.

Description

Technical Field

[0001] The present application relates to the technical field of substrate cutting, and in particular to a multi-point collaboratively optimized insulation board cutting method and device. Background Art

[0002] In the construction industry, there is a huge demand for thermal insulation materials, so reducing material waste is of great significance to saving costs and resources. Traditional cutting methods often rely on manual operations, which are inefficient and difficult to ensure accuracy.

[0003] At present, the existing insulation board cutting technology mainly relies on manual operation and experience judgment, lacking accurate component detection and cutting parameter optimization process. In addition, the traditional cutting method also has certain limitations in material utilization, cutting efficiency and environmental protection, which need to be overcome through technological innovation.

[0004] In summary, the prior art lacks component detection of the insulation board substrate and optimization of the cutting point array, resulting in poor consistency in the composition of the insulation board after cutting and low dimensional accuracy, further affecting the quality and performance of the insulation board. Summary of the invention

[0005] The purpose of this application is to provide a multi-point collaboratively optimized insulation board cutting method and device to solve the technical problem that the prior art lacks composition detection of the insulation board substrate and cutting point array optimization, resulting in poor composition consistency and low dimensional accuracy of the cut insulation board, which further affects the quality and performance of the insulation board.

[0006] In view of the above problems, the present application provides a multi-point collaboratively optimized insulation board cutting method and device.

[0007] In a first aspect, the present application provides a multi-point collaborative optimization insulation board cutting method, the method is implemented by a multi-point collaborative optimization insulation board cutting device, wherein the method includes: performing component detection on the insulation board substrate to be cut, and constructing a component characteristic information distribution, wherein the insulation board substrate needs to be cut into an insulation board of preset specifications; according to the component characteristic information distribution, optimizing the cutting point array to obtain an optimal cutting point array, wherein the optimal cutting point array includes multiple optimal cutting points to form a cutting route, and the purpose of optimization is to improve the component consistency of the insulation board after cutting; based on the cutting point array, performing multi-point collaborative cutting optimization on the cutting parameters of the multiple optimal cutting points, and in the optimization process, predicting the cutting specification deviation coefficient caused by the cutting parameters, and obtaining a cutting parameter combination library with the smallest cutting specification deviation coefficient; according to the cutting route and the component characteristic information distribution, obtaining the cutting line component characteristic information distribution by index detection; according to the cutting line component characteristic information distribution, with the purpose of reducing the degree of influence of cutting on the performance of the insulation board material, optimizing the cutting parameter combination in the cutting parameter combination library to obtain the optimal cutting parameter combination, and cutting the insulation board substrate in combination with the cutting point array.

[0008] In the second aspect, the present application also provides a multi-point collaboratively optimized insulation board cutting device, which is used to execute a multi-point collaboratively optimized insulation board cutting method as described in the first aspect, wherein the device includes: a component detection module, the component detection module is used to perform component detection on the insulation board substrate to be cut, and construct a component characteristic information distribution, wherein the insulation board substrate needs to be cut into insulation boards of preset specifications; an optimal cutting point array acquisition module, the optimal cutting point array acquisition module is used to optimize the cutting point array according to the component characteristic information distribution, and obtain an optimal cutting point array, wherein the optimal cutting point array includes multiple optimal cutting points to form a cutting route, and the purpose of the optimization is to improve the composition consistency of the insulation board after cutting; a cutting optimization module The cutting optimization module is used to perform multi-point collaborative cutting optimization on the cutting parameters of multiple optimal cutting points based on the cutting point array. During the optimization process, the cutting specification deviation coefficient caused by the cutting parameters is predicted to obtain a cutting parameter combination library with the smallest cutting specification deviation coefficient; a feature information detection module is used to obtain the cutting line component feature information distribution by index detection according to the cutting route and component feature information distribution; a substrate cutting module is used to optimize the cutting parameter combination in the cutting parameter combination library according to the cutting line component feature information distribution, with the purpose of reducing the degree of influence of cutting on the performance of the insulation board material, to obtain the optimal cutting parameter combination, and cut the insulation board substrate in combination with the cutting point array.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] By performing component detection on the insulation board substrate to be cut, a component characteristic information distribution is constructed, wherein the insulation board substrate needs to be cut into insulation boards of preset specifications; based on the component characteristic information distribution, a cutting point array is optimized to obtain an optimal cutting point array, wherein the optimal cutting point array includes multiple optimal cutting points to form a cutting route, and the purpose of the optimization is to improve the component consistency of the insulation board after cutting; based on the cutting point array, multi-point collaborative cutting optimization is performed on the cutting parameters of the multiple optimal cutting points, and in the optimization process, the cutting specification deviation coefficient caused by the cutting parameters is predicted to obtain a cutting parameter combination library with the smallest cutting specification deviation coefficient; based on the cutting route and component Characteristic information distribution, index detection obtains the distribution of cutting line component characteristic information; according to the cutting line component characteristic information distribution, with the purpose of reducing the influence of cutting on the performance of the insulation board material, the cutting parameter combination is optimized in the cutting parameter combination library to obtain the optimal cutting parameter combination, and the insulation board substrate is cut in combination with the cutting point array, which effectively solves the technical problem that the prior art lacks component detection of the insulation board substrate and optimization of the cutting point array, resulting in poor consistency of the composition of the insulation board after cutting and low dimensional accuracy, which further affects the quality and performance of the insulation board. The impact of cutting on material properties is reduced by optimizing the cutting parameters, thereby improving the overall quality and performance of the insulation board.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0013] Figure 1 A schematic flow chart of a multi-point collaboratively optimized insulation board cutting method for the present application.

[0014] Figure 2 This is a schematic structural diagram of a multi-point collaboratively optimized insulation board cutting device for the present application.

[0015] Description of reference numerals:

[0016] Component detection module 11, optimal cutting point array acquisition module 12, cutting optimization module 13, feature information detection module 14, substrate cutting module 15. DETAILED DESCRIPTION

[0017] The present application provides a multi-point collaboratively optimized insulation board cutting method and device, which solves the technical problem in the prior art that the insulation board after cutting has poor consistency in composition and low dimensional accuracy, further affecting the quality and performance of the insulation board due to the lack of composition detection of the insulation board substrate and optimization of the cutting point array, and reduces the impact of cutting on material properties by optimizing the cutting parameters, thereby improving the overall quality and performance of the insulation board.

[0018] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0019] Embodiment 1

[0020] Please see attached Figure 1 The present application provides a multi-point collaborative optimization insulation board cutting method, wherein the method is applied to a multi-point collaborative optimization insulation board cutting device, and the method specifically includes the following steps:

[0021] S1: Detecting the composition of the insulation board substrate to be cut and constructing a distribution of component characteristic information, wherein the insulation board substrate needs to be cut into insulation boards of preset specifications.

[0022] Specifically, the insulation board substrate to be cut is scanned using spectral analysis techniques, such as infrared spectroscopy or Raman spectroscopy. Non-destructive testing techniques, such as X-ray diffraction or ultrasonic testing, are used to analyze the internal structure of the insulation board substrate, such as crystal structure, density distribution, etc. The data obtained from the test is input into the computer-aided design (CAD) system, and a distribution map of the composition characteristic information of the substrate is generated using a software algorithm. This distribution map will show the distribution of different components in the substrate.

[0023] S2: Optimizing the cutting point array according to the distribution of the component characteristic information to obtain an optimal cutting point array, wherein the optimal cutting point array includes multiple optimal cutting points to form a cutting route, and the purpose of the optimization is to improve the consistency of the components of the insulation board after cutting.

[0024] Specifically, using the data obtained from the composition detection, the composition distribution of the insulation board substrate is analyzed through computer algorithms to identify areas with large composition fluctuations. According to the preset specifications and shape requirements of the insulation board, the optimal array of cutting points is calculated. These cutting points need to avoid areas with uneven composition to ensure that each cut insulation board section has the most consistent composition possible. Use optimization algorithms, such as genetic algorithms, particle swarm optimization, or machine learning algorithms to find the optimal array of cutting points. These algorithms can find the best balance between multiple cutting points to ensure the overall composition distribution of the insulation board substrate, as well as the efficiency of the cutting path, avoid unnecessary overlaps or gaps, and reduce material waste. Once the optimal array of cutting points is determined, cutting routes can be generated. These routes will guide cutting equipment, such as CNC cutting machines, on how to move to cut out the insulation board. The cutting route will minimize unnecessary movement, improve cutting efficiency, and ensure the stability and accuracy of the material during the cutting process.

[0025] S3: Based on the cutting point array, multi-point collaborative cutting optimization is performed on the cutting parameters of multiple optimal cutting points. During the optimization process, the cutting specification deviation coefficient caused by the cutting parameters is predicted to obtain a cutting parameter combination library with the smallest cutting specification deviation coefficient.

[0026] Specifically, after determining the optimal array of cutting points, the cutting parameters of these cutting points are optimized. These parameters include cutting speed, cutting depth, cutting pressure, tool selection, etc. The optimization is that the cutting deviation caused by the difference in material properties or cutting equipment can be predicted and minimized. Use machine learning models or physical models to predict the cutting specification deviation under different cutting parameter combinations. These models are trained based on historical data, material properties, and equipment performance. Tool wear, material rebound, temperature changes, etc., all of these factors may cause cutting deviations. By using optimization algorithms such as gradient descent or Bayesian optimization, find the cutting parameter combination that can minimize the cutting specification deviation coefficient. Store these parameters in a cutting parameter combination library.

[0027] S4: According to the cutting route and the component characteristic information distribution, index detection is performed to obtain the cutting line component characteristic information distribution.

[0028] Specifically, index detection is a method for locating and extracting the component characteristic information of the insulation board substrate according to the cutting route. In this way, it can be ensured that each point on the cutting line can correspond to the component characteristic information of the substrate. Index detection can be performed using a computer-aided design CAD system or dedicated data processing software that can process the component characteristic information distribution data and extract relevant information based on the cutting route. Once the index detection is completed, the component characteristic information distribution on the cutting line is obtained. This information includes the component content and distribution uniformity on the cutting line.

[0029] S5: Based on the distribution of the cutting line component characteristic information, the cutting parameter combination is optimized in the cutting parameter combination library for the purpose of reducing the impact of cutting on the performance of the insulation board material, and the optimal cutting parameter combination is obtained. The insulation board substrate is cut in combination with the cutting point array.

[0030] Specifically, the distribution of the cutting line component characteristic information can be used to more accurately predict the impact of different parameters on material properties during the cutting process. By adjusting cutting parameters such as cutting speed, cutting pressure, tool type and cutting path, the thermal damage, stress concentration and structural deformation of the material can be reduced, thereby reducing the impact on the performance of the insulation board material. In the cutting parameter combination library, based on the distribution of the cutting line component characteristic information, optimization algorithms such as genetic algorithms, simulated annealing algorithms or particle swarm optimization are used to find the optimal cutting parameter combination. The optimization algorithm searches through multiple parameter combinations to find the optimal solution that can minimize the impact of cutting on material properties. Once the optimal cutting parameter combination is obtained, these parameters will be combined with the optimal cutting point array. Cutting equipment, such as CNC cutting machines, will perform precise cutting based on these parameters and the cutting point array to ensure cutting quality and material properties.

[0031] Furthermore, step S1 of the present application also includes:

[0032] Insulation material composition is detected at multiple positions of the insulation board substrate to be cut to obtain a composition feature information set; a composition feature information array is constructed based on the position information of the multiple positions in combination with the composition feature information set; and the composition feature information array is interpolated and rendered to obtain the composition feature information distribution.

[0033] Specifically, samples are taken at multiple locations on the insulation board substrate, and spectral analysis, chemical analysis or other component analysis techniques are used to detect the composition of the insulation material. This includes key information such as the chemical composition, density, and crystallinity of the substrate. The data obtained from the detection are gathered together to form a component characteristic information set. This set contains the component information of multiple locations on the substrate. Based on the position information of multiple locations on the insulation board substrate, combined with the component characteristic information set, a component characteristic information array can be constructed using data analysis. This array shows the component characteristics of different locations on the substrate, which helps to identify the uniformity and uneven areas of the composition. The component characteristic information array is interpolated and rendered to fill the information gaps between the detection points and obtain a more continuous and complete distribution of component characteristic information. Interpolation rendering can use linear interpolation, polynomial interpolation, or Kriging interpolation to generate a smooth information distribution map.

[0034] Furthermore, step S2 of the present application also includes:

[0035] The preset specification is used to perform random fitting on the component characteristic information distribution to obtain a first cutting point array and a first simulated cutting insulation board; according to the first cutting point array, the first cutting component characteristic information distribution is divided to obtain the first simulated cutting insulation board; the first consistency information of the first cutting component characteristic information distribution is calculated; the preset specification is continued to be used to perform random fitting on the component characteristic information distribution until convergence, and the cutting point array with the largest consistency information is selected, and the output is the optimal cutting point array.

[0036] Specifically, on the component characteristic information distribution map, random fitting is performed using the preset insulation board specifications. A starting point is randomly selected on the distribution map, and then a virtual cutting template is placed according to the size and shape of the insulation board. Each random fitting generates a cutting point array, which defines the cutting boundary of the insulation board. At the same time, a simulated cut insulation board is also generated, which represents the insulation board after cutting according to the current cutting point array. According to the first cutting point array, the cutting component characteristic information distribution of the first simulated cut insulation board is divided within the component characteristic information distribution. This distribution describes the component characteristics of each area in the simulated cut insulation board. The first cut component characteristic information distribution is analyzed and the consistency information is calculated. The consistency information can be the standard deviation, uniformity or other statistical indicators of the component content, which is used to evaluate the consistency of the insulation board components after cutting. Repeat the random fitting process, generate a new cutting point array and simulated cut insulation board each time, and calculate their consistency information. This process continues until the cutting point array with the largest consistency information is found, which is considered to be the best cutting solution. Once converged, that is, the cutting point array with the largest consistency information is found, this array is output as the optimal cutting point array.

[0037] Furthermore, step S3 of the present application also includes:

[0038] Acquire a cutting parameter combination space, wherein the cutting parameter combination space is obtained by combining cutting parameter ranges of a plurality of cutting points; construct a cutting optimization function for evaluating the cutting parameter combination based on reducing a cutting specification deviation coefficient; ; Among them, COF is the cutting fitness, M is the number of multiple optimal cutting points, The cutting specification deviation coefficient when the i-th cutting point is cut according to the optimized cutting parameter combination; a plurality of first cutting parameter combinations are randomly generated in the cutting parameter combination space, and cutting specification deviation predictions are performed to obtain a plurality of first cutting specification deviation coefficient sets, wherein a cutting deviation predictor is trained by collecting sample cutting parameter combinations and sample cutting specification deviation coefficient sets, and cutting specification deviation predictions are performed on the plurality of first cutting parameter combinations; a plurality of first cutting fitnesses are calculated based on the plurality of first cutting fitnesses; the plurality of first cutting parameter combinations are optimized and updated based on the plurality of first cutting fitnesses until convergence to obtain a cutting parameter combination library.

[0039] Specifically, the cutting parameter combination space is composed of all possible cutting parameter combinations. Each cutting point has a series of cutting parameters, such as cutting speed, cutting depth, cutting pressure, etc., and these parameters have their own acceptable ranges. The cutting parameter combination space can be obtained by enumerating all possible parameter combinations. The cutting optimization function is used to evaluate the advantages and disadvantages of different cutting parameter combinations. The function is usually constructed based on the goal of reducing the cutting specification deviation coefficient. Multiple first cutting parameter combinations are randomly generated in the cutting parameter combination space, and the cutting specification deviation of these combinations is predicted using a cutting deviation predictor. The cutting deviation predictor can be trained by a machine learning algorithm, using historical data and sample cutting parameter combinations to predict the cutting specification deviation coefficient. According to the predicted cutting specification deviation coefficient set, the cutting fitness of each cutting parameter combination is calculated. According to the cutting fitness, the cutting parameter combination is optimized and updated. The optimization algorithm can be a genetic algorithm, a simulated annealing algorithm, or other heuristic search algorithm. The optimization process is repeated until the cutting parameter combination with the highest cutting fitness is found, or a preset convergence condition is reached. The cutting parameter combination finally optimized is stored in the cutting parameter combination library.

[0040] Furthermore, the present application also includes:

[0041] According to the multiple first cutting fitnesses, the first cutting parameter combination with the largest first cutting fitness is selected as the cutting optimization direction; with the cutting optimization direction as the adjustment direction, the other multiple first cutting parameter combinations are adjusted, and the cutting specification deviation is predicted and calculated to obtain multiple second cutting fitnesses; according to the multiple second cutting fitnesses, the cutting optimization direction is updated; the optimization is continued until convergence, and the final multiple converged cutting parameter combinations are output to obtain a cutting parameter combination library.

[0042] Specifically, according to the calculated multiple first cutting fitnesses, the first cutting parameter combination with the highest fitness is selected as the cutting optimization direction. This combination represents the best cutting parameter setting in the current iteration. Based on the selected cutting optimization direction, the other multiple first cutting parameter combinations are adjusted. The purpose of the adjustment is to explore the parameter space and find a better cutting parameter combination. For the adjusted multiple cutting parameter combinations, the cutting deviation predictor is used to predict the cutting specification deviation. According to the predicted cutting specification deviation, the second cutting fitness of each adjusted cutting parameter combination is calculated. The second cutting fitness is used to evaluate the performance of the adjusted parameter combination relative to the optimization direction. According to the multiple second cutting fitnesses, the cutting optimization direction is updated. If a new cutting parameter combination shows a higher fitness, this new combination is used as a new optimization direction. Repeat the process of adjustment, prediction, calculation and update to continuously optimize the cutting parameter combination. This process continues until a set of converged cutting parameter combinations is found, that is, the cutting fitness is no longer significantly improved. Finally, the multiple converged cutting parameter combinations are output to form a cutting parameter combination library. This library contains a variety of optimized cutting parameter combinations.

[0043] Furthermore, step S5 of the present application also includes:

[0044] Training a cutting performance impact predictor; using the cutting performance impact predictor to predict the cutting performance impact of the cutting line component characteristic information distribution and multiple cutting parameter combinations in the cutting parameter combination library to obtain multiple thermal insulation performance impact parameters; based on the multiple thermal insulation performance impact parameters, optimizing selection is performed in the cutting parameter combination library to obtain the optimal cutting parameter combination with the smallest thermal insulation performance impact parameter.

[0045] Specifically, the cutting performance impact predictor is a model used to predict the impact of different cutting parameter combinations on the thermal insulation performance of the insulation board. The training data set includes historical cutting data, insulation board component characteristics, cutting parameters and corresponding thermal insulation performance results. Machine learning techniques such as regression analysis, support vector machine, neural network, etc. are used to train the predictor so that it can predict thermal insulation performance based on the input cutting parameters and component characteristics. The trained cutting performance impact predictor is used to predict the distribution of cutting line component characteristic information and multiple cutting parameter combinations in the cutting parameter combination library. The predictor will output one or more thermal insulation performance impact parameters for each parameter combination, which quantify the possible impact of the cutting operation on the thermal insulation performance of the insulation board. Based on the predicted multiple thermal insulation performance impact parameters, an optimization selection is performed in the cutting parameter combination library. The goal is to find those cutting parameter combinations with the smallest thermal insulation performance impact parameters, because these combinations have the smallest impact on the thermal insulation performance of the insulation board. By comparing the thermal insulation performance impact parameters of different cutting parameter combinations, the parameter combination with the smallest impact is selected as the optimal cutting parameter combination. This optimal combination will be used in the actual cutting process to ensure that the cut insulation board has good thermal insulation performance.

[0046] Furthermore, the present application also includes:

[0047] According to the cutting data records of the insulation board substrate, the sample cutting line component characteristic information distribution set and the sample cutting parameter combination set are collected, and according to the change range of the thermal insulation performance of the insulation material after cutting, the sample thermal insulation performance influencing parameter set is identified and obtained; the sample cutting line component characteristic information distribution set, the sample cutting parameter combination set and the sample thermal insulation performance influencing parameter set are used to train the cutting performance impact predictor until convergence, so as to obtain the cutting performance impact predictor.

[0048] Specifically, sample data is collected from historical cutting data records, including the distribution of cutting line component feature information, cutting parameter combinations, and the change range of thermal insulation performance of thermal insulation materials after cutting. The cutting line component feature information distribution set contains the component information of the thermal insulation board substrate on different cutting lines. The sample cutting parameter combination set includes the historical combination of various cutting parameters. The sample thermal insulation performance influencing parameter set records the change of thermal insulation performance after the cutting operation. The thermal insulation performance change range of the thermal insulation material after cutting is measured, such as thermal conductivity, thermal resistance, etc. These data are used to identify the sample thermal insulation performance influencing parameters, which will be used as the target variables for training the cutting performance impact predictor. The collected sample data set, including the cutting line component feature information distribution set, the sample cutting parameter combination set, and the sample thermal insulation performance influencing parameter set, is used to train the cutting performance impact predictor. A suitable machine learning algorithm, such as random forest, gradient boosting machine, or neural network, is selected to build a prediction model. The training process adjusts and verifies the model parameters until the model converges, that is, the prediction error of the model reaches an acceptable level. After training, the obtained cutting performance influence predictor can predict the thermal insulation performance influence parameters according to the input cutting line component characteristic information and cutting parameter combination. This predictor can be used in the actual cutting parameter optimization process to help select the cutting parameter combination with the least influence on thermal insulation performance.

[0049] In summary, the multi-point collaborative optimization insulation board cutting method provided by the present application has the following technical effects:

[0050] By performing component detection on the insulation board substrate to be cut, a component characteristic information distribution is constructed, wherein the insulation board substrate needs to be cut into insulation boards of preset specifications; based on the component characteristic information distribution, a cutting point array is optimized to obtain an optimal cutting point array, wherein the optimal cutting point array includes multiple optimal cutting points to form a cutting route, and the purpose of the optimization is to improve the component consistency of the insulation board after cutting; based on the cutting point array, multi-point collaborative cutting optimization is performed on the cutting parameters of the multiple optimal cutting points, and in the optimization process, the cutting specification deviation coefficient caused by the cutting parameters is predicted to obtain a cutting parameter combination library with the smallest cutting specification deviation coefficient; based on the cutting route and component Characteristic information distribution, index detection obtains the distribution of cutting line component characteristic information; according to the cutting line component characteristic information distribution, with the purpose of reducing the influence of cutting on the performance of the insulation board material, the cutting parameter combination is optimized in the cutting parameter combination library to obtain the optimal cutting parameter combination, and the insulation board substrate is cut in combination with the cutting point array, which effectively solves the technical problem that the prior art lacks component detection of the insulation board substrate and optimization of the cutting point array, resulting in poor consistency of the composition of the insulation board after cutting and low dimensional accuracy, which further affects the quality and performance of the insulation board. The impact of cutting on material properties is reduced by optimizing the cutting parameters, thereby improving the overall quality and performance of the insulation board.

[0051] Embodiment 2

[0052] Based on the same inventive concept as the multi-point collaboratively optimized insulation board cutting method in the aforementioned embodiment, the present application also provides a multi-point collaboratively optimized insulation board cutting device, please refer to the attached Figure 2 , the device comprises:

[0053] The component detection module 11 is used to detect the components of the insulation board substrate to be cut and construct component characteristic information distribution, wherein the insulation board substrate needs to be cut into insulation boards of preset specifications.

[0054] The optimal cutting point array acquisition module 12 is used to optimize the cutting point array according to the distribution of the component characteristic information to obtain the optimal cutting point array, wherein the optimal cutting point array includes multiple optimal cutting points to form a cutting route, and the purpose of the optimization is to improve the consistency of the composition of the insulation board after cutting.

[0055] The cutting optimization module 13 is used to perform multi-point collaborative cutting optimization on the cutting parameters of multiple optimal cutting points based on the cutting point array. During the optimization process, the cutting specification deviation coefficient caused by the cutting parameters is predicted to obtain a cutting parameter combination library with the smallest cutting specification deviation coefficient.

[0056] The feature information detection module 14 is used to obtain the cutting line component feature information distribution through index detection according to the cutting route and component feature information distribution.

[0057] The substrate cutting module 15 is used to optimize the cutting parameter combination in the cutting parameter combination library according to the distribution of the cutting line component characteristic information, with the purpose of reducing the influence of cutting on the performance of the insulation board material, obtain the optimal cutting parameter combination, and cut the insulation board substrate in combination with the cutting point array.

[0058] Furthermore, the component detection module 11 in the device is also used for:

[0059] Insulation material composition is detected at multiple positions of the insulation board substrate to be cut to obtain a composition feature information set; a composition feature information array is constructed based on the position information of the multiple positions in combination with the composition feature information set; and the composition feature information array is interpolated and rendered to obtain the composition feature information distribution.

[0060] Furthermore, the optimal cutting point array acquisition module 12 in the device is also used for:

[0061] The preset specification is used to perform random fitting on the component characteristic information distribution to obtain a first cutting point array and a first simulated cutting insulation board; according to the first cutting point array, the first cutting component characteristic information distribution is divided to obtain the first simulated cutting insulation board; the first consistency information of the first cutting component characteristic information distribution is calculated; the preset specification is continued to be used to perform random fitting on the component characteristic information distribution until convergence, and the cutting point array with the largest consistency information is selected, and the output is the optimal cutting point array.

[0062] Furthermore, the cutting optimization module 13 in the device is also used for:

[0063] Acquire a cutting parameter combination space, wherein the cutting parameter combination space is obtained by combining cutting parameter ranges of a plurality of cutting points; construct a cutting optimization function for evaluating the cutting parameter combination based on reducing a cutting specification deviation coefficient; ; Among them, COF is the cutting fitness, M is the number of multiple optimal cutting points, The cutting specification deviation coefficient when the i-th cutting point is cut according to the optimized cutting parameter combination; a plurality of first cutting parameter combinations are randomly generated in the cutting parameter combination space, and cutting specification deviation predictions are performed to obtain a plurality of first cutting specification deviation coefficient sets, wherein a cutting deviation predictor is trained by collecting sample cutting parameter combinations and sample cutting specification deviation coefficient sets, and cutting specification deviation predictions are performed on the plurality of first cutting parameter combinations; a plurality of first cutting fitnesses are calculated based on the plurality of first cutting fitnesses; the plurality of first cutting parameter combinations are optimized and updated based on the plurality of first cutting fitnesses until convergence to obtain a cutting parameter combination library.

[0064] Furthermore, the device further comprises an optimization direction updating module, and the optimization parameter updating module is used for:

[0065] According to the multiple first cutting fitnesses, the first cutting parameter combination with the largest first cutting fitness is selected as the cutting optimization direction; with the cutting optimization direction as the adjustment direction, the other multiple first cutting parameter combinations are adjusted, and the cutting specification deviation is predicted and calculated to obtain multiple second cutting fitnesses; according to the multiple second cutting fitnesses, the cutting optimization direction is updated; the optimization is continued until convergence, and the final multiple converged cutting parameter combinations are output to obtain a cutting parameter combination library.

[0066] Furthermore, the substrate cutting module 15 in the device is also used for:

[0067] Training a cutting performance impact predictor; using the cutting performance impact predictor to predict the cutting performance impact of the cutting line component characteristic information distribution and multiple cutting parameter combinations in the cutting parameter combination library to obtain multiple thermal insulation performance impact parameters; based on the multiple thermal insulation performance impact parameters, optimizing selection is performed in the cutting parameter combination library to obtain the optimal cutting parameter combination with the smallest thermal insulation performance impact parameter.

[0068] Furthermore, the device further comprises a cutting performance impact predictor acquisition module, wherein the cutting performance impact predictor acquisition module is used to:

[0069] According to the cutting data records of the insulation board substrate, the sample cutting line component characteristic information distribution set and the sample cutting parameter combination set are collected, and according to the change range of the thermal insulation performance of the insulation material after cutting, the sample thermal insulation performance influencing parameter set is identified and obtained; the sample cutting line component characteristic information distribution set, the sample cutting parameter combination set and the sample thermal insulation performance influencing parameter set are used to train the cutting performance impact predictor until convergence, so as to obtain the cutting performance impact predictor.

[0070] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The multi-point collaboratively optimized insulation board cutting method and specific examples in the first embodiment are also applicable to the multi-point collaboratively optimized insulation board cutting device in the present embodiment. Through the above detailed description of the multi-point collaboratively optimized insulation board cutting method, those skilled in the art can clearly know the multi-point collaboratively optimized insulation board cutting device in the present embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method description.

[0071] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0072] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A multi-point collaborative optimization insulation board cutting method, characterized in that: The method comprises: Performing component detection on the insulation board substrate to be cut and constructing component characteristic information distribution, wherein the insulation board substrate needs to be cut into insulation boards of preset specifications; According to the distribution of the component characteristic information, the cutting point array is optimized to obtain an optimal cutting point array, wherein the optimal cutting point array includes multiple optimal cutting points to form a cutting route, and the purpose of the optimization is to improve the consistency of the components of the insulation board after cutting; Based on the cutting point array, multi-point collaborative cutting optimization is performed on the cutting parameters of multiple optimal cutting points. During the optimization process, the cutting specification deviation coefficient caused by the cutting parameters is predicted to obtain a cutting parameter combination library with the smallest cutting specification deviation coefficient; According to the cutting route and the component characteristic information distribution, index detection is performed to obtain the cutting line component characteristic information distribution; According to the distribution of the cutting line component characteristic information, with the purpose of reducing the impact of cutting on the performance of the insulation board material, the cutting parameter combination is optimized in the cutting parameter combination library to obtain the optimal cutting parameter combination, and the insulation board substrate is cut in combination with the cutting point array.

2. The multi-point collaborative optimization insulation board cutting method according to claim 1 is characterized in that: The composition of the insulation board substrate to be cut is detected, and the composition characteristic information distribution is constructed, including: Conducting insulation material component detection at multiple locations of the insulation board substrate to be cut to obtain a set of component characteristic information; Constructing a component characteristic information array according to the position information of the plurality of positions in combination with the component characteristic information set; The component feature information array is interpolated and rendered to obtain the component feature information distribution.

3. The multi-point collaborative optimization insulation board cutting method according to claim 1, characterized in that: According to the distribution of the component characteristic information, the cutting point array is optimized to obtain the optimal cutting point array, including: The preset specification is used to perform random fitting on the distribution of the component characteristic information to obtain a first cutting point array and a first simulated cutting insulation board; According to the first cutting point array, dividing within the component characteristic information distribution to obtain a first cutting component characteristic information distribution of a first simulated cutting insulation board; Calculate and obtain first consistency information of the first cutting component feature information distribution; Continue to use the preset specifications to perform random fitting on the component feature information distribution until convergence, select the cutting point array with the largest consistency information, and output it as the optimal cutting point array.

4. The multi-point collaborative optimization insulation board cutting method according to claim 1, characterized in that: Based on the cutting point array, the cutting parameters of multiple optimal cutting points are optimized by multi-point collaborative cutting. During the optimization process, the cutting specification deviation coefficient caused by the mutual influence of the cutting parameters is predicted, including: Acquire a cutting parameter combination space, wherein the cutting parameter combination space is obtained by combining cutting parameter ranges of multiple cutting points; Based on reducing the cutting specification deviation coefficient, a cutting optimization function is constructed to evaluate the cutting parameter combination; ； Among them, COF is the cutting fitness, M is the number of multiple optimal cutting points, is the cutting specification deviation coefficient when the i-th cutting point is cut according to the optimized cutting parameter combination; A plurality of first cutting parameter combinations are randomly generated in the cutting parameter combination space, cutting specification deviations are predicted, and a plurality of first cutting specification deviation coefficient sets are obtained, wherein a cutting deviation predictor is trained by collecting sample cutting parameter combinations and sample cutting specification deviation coefficient sets, and cutting specification deviations are predicted for the plurality of first cutting parameter combinations; Calculating and obtaining a plurality of first cutting fitnesses according to the plurality of first cutting specification deviation coefficient sets; According to the multiple first cutting fitnesses, the multiple first cutting parameter combinations are optimized and updated until convergence, so as to obtain a cutting parameter combination library.

5. The multi-point collaborative optimization insulation board cutting method according to claim 4 is characterized in that: According to the plurality of first cutting fitnesses, the plurality of first cutting parameter combinations are optimized and updated, including: According to the multiple first cutting fitnesses, selecting a first cutting parameter combination with the largest first cutting fitness as a cutting optimization direction; Taking the cutting optimization direction as the adjustment direction, adjusting other multiple first cutting parameter combinations, and performing cutting specification deviation prediction and calculation to obtain multiple second cutting fitnesses; According to the multiple second cutting fitnesses, the cutting optimization direction is updated; Continue to optimize until convergence, output the final multiple convergent cutting parameter combinations, and obtain a cutting parameter combination library.

6. The multi-point collaborative optimization insulation board cutting method according to claim 1, characterized in that: According to the distribution of the cutting line component characteristic information, in order to reduce the influence of cutting on the performance of the insulation board material, the cutting parameter combination is optimized in the cutting parameter combination library to obtain the optimal cutting parameter combination, including: Training a cutting performance impact predictor; The cutting performance influence predictor is used to predict the cutting performance influence of the cutting line component characteristic information distribution and multiple cutting parameter combinations in the cutting parameter combination library to obtain multiple thermal insulation performance influence parameters; According to the plurality of thermal insulation performance influencing parameters, an optimization selection is performed in the cutting parameter combination library to obtain an optimal cutting parameter combination with the smallest thermal insulation performance influencing parameter.

7. The multi-point collaborative optimization insulation board cutting method according to claim 6, characterized in that: Training of cutting performance impact predictors, including: According to the cutting data record of the insulation board substrate, the sample cutting line component characteristic information distribution set and the sample cutting parameter combination set are collected, and according to the change range of the insulation performance of the insulation material after cutting, the sample insulation performance influencing parameter set is marked and obtained; The sample cutting line component characteristic information distribution set, the sample cutting parameter combination set and the sample thermal insulation performance influencing parameter set are used to train a cutting performance influencing predictor until convergence, thereby obtaining a cutting performance influencing predictor.

8. A multi-point collaborative optimization insulation board cutting device, characterized in that: For implementing the steps of the method according to any one of claims 1 to 7, the device comprises: A component detection module, the component detection module is used to detect the components of the insulation board substrate to be cut and construct component characteristic information distribution, wherein the insulation board substrate needs to be cut into insulation boards of preset specifications; An optimal cutting point array acquisition module, the optimal cutting point array acquisition module is used to optimize the cutting point array according to the distribution of the component characteristic information to obtain the optimal cutting point array, wherein the optimal cutting point array includes multiple optimal cutting points to form a cutting route, and the purpose of the optimization is to improve the consistency of the components of the insulation board after cutting; A cutting optimization module, which is used to perform multi-point collaborative cutting optimization on cutting parameters of multiple optimal cutting points based on the cutting point array, and in the optimization process, predict the cutting specification deviation coefficient caused by the cutting parameters to obtain a cutting parameter combination library with the smallest cutting specification deviation coefficient; A feature information detection module, the feature information detection module is used to obtain the cutting line component feature information distribution through index detection according to the cutting route and component feature information distribution; A substrate cutting module is used to optimize the cutting parameter combination in the cutting parameter combination library according to the distribution of the cutting line component characteristic information, with the purpose of reducing the influence of cutting on the performance of the insulation board material, obtain the optimal cutting parameter combination, and cut the insulation board substrate in combination with the cutting point array.

Images