Multi-channel intelligent collaborative forming control method and system based on carbonization equipment

Abstract

The invention relates to the technical field of program control, and discloses a multi-channel intelligent collaborative forming control method and system based on carbonization equipment. The method comprises the steps that carbonization forming monitoring equipment is installed, and the material carbonization state in a current area is monitored in real time based on the installed carbonization forming monitoring equipment; meanwhile, whether adjustment is needed or not is judged in the mode that the material carbonization state, monitored in real time, in the current area is compared with the stored optimal material carbonization parameter information; a control instruction is generated according to a comparison result, so that the carbonization state of the material in the current area is regulated and controlled; according to the invention, the accuracy and real-time performance of intelligent collaborative forming control are improved through real-time monitoring, real-time comparison and real-time regulation and control.

Description

Technical Field

[0001] The present invention relates to the technical field of program control, and specifically to a multi-channel intelligent collaborative forming control method and system based on a carbonization device. Background Art

[0002] Fiber carbonization is easily affected by the temperature and pressure in the carbonization device, which is complex and variable. Operators make judgments solely based on experience, which is highly subjective and results in inconsistent fiber carbonization degrees.

[0003] In the existing Chinese patent application technology CN115993807B, by reading the production control process of silicon carbide, initial control nodes are arranged; at the same time, historical processing production information is collected, production influence characteristics are extracted, and feature compensation is calculated for the extraction results of the production influence characteristics; at the same time, key nodes are determined; real-time production data of the key nodes is monitored; when the detection output result is abnormal; the key nodes are repositioned, and optimization compensation parameters are generated based on the abnormal detection result and the monitoring result of the repositioned key nodes. However, since it is judged based on the abnormal output result, there are certain limitations. Summary of the Invention

[0004] (1) Technical Problems to be Solved

[0005] Aiming at the deficiencies of the prior art, the present invention provides a multi-channel intelligent collaborative forming control method and system based on a carbonization device, which has the advantages of accuracy, real-time, etc., and solves the problem that operators make judgments solely based on experience, which is highly subjective and results in inconsistent fiber carbonization degrees.

[0006] (2) Technical Solutions

[0007] To solve the above technical problem that operators make judgments solely based on experience, which is highly subjective and results in inconsistent fiber carbonization degrees, the present invention provides the following technical solutions:

[0008] Embodiment 1

[0009] This embodiment discloses a multi-channel intelligent collaborative forming control method based on a carbonization device, which specifically includes the following steps:

[0010] S1. Collect carbonization forming images and parameter information corresponding to the carbonization forming images, and construct a carbonization forming data sample set;

[0011] S2. Process the carbonization forming images and parameter information corresponding to the carbonization forming images in the sample set to obtain the processed carbonization forming images and parameter information corresponding to the carbonization forming images;

[0012] S3. Collect the scoring data of the processed carbonized forming images and the corresponding parameter information of the carbonized forming images, and construct a training set of the carbonized forming images and the corresponding parameter information of the carbonized forming images;

[0013] S4. Optimize the processed carbonized forming images and the corresponding parameter information of the carbonized forming images in the training set based on the multi-objective genetic algorithm to obtain the optimal parameter information of the carbonized forming;

[0014] S5. Install carbonized forming monitoring equipment to monitor the carbonization state and carbonization image data of the materials in the current area in real time, and regulate the carbonization state of the materials in the current area based on the obtained optimal parameter information of the carbonized forming.

[0015] In the present invention, by collecting the carbonized forming images and the parameter information of the corresponding carbonized forming images, a carbonized forming data sample set is constructed. At the same time, the carbonized forming images and the parameter information of the corresponding carbonized forming images in the sample set are processed, and the scoring data of the processed carbonized forming images and the corresponding parameter information of the carbonized forming images are collected to construct a training set of the carbonized forming images and the corresponding parameter information of the carbonized forming images. At the same time, the data in the training set is optimized by the multi-objective genetic algorithm to obtain the optimal parameter information, and the carbonization state of the materials in the current area is regulated based on the obtained optimal parameter information, thereby improving the accuracy and real-time performance of the intelligent collaborative forming control.

[0016] Preferably, the processing of the carbonized forming images and the parameter information of the corresponding carbonized forming images in the sample set includes the following steps:

[0017] S21. Process the carbonized forming images in the sample set to obtain the processed carbonized forming images;

[0018] S22. Process the parameter information of the corresponding carbonized forming images in the sample set to obtain the processed parameter information of the corresponding carbonized forming images.

[0019] Preferably, the processing of the carbonized forming images in the sample set to obtain the processed carbonized forming images includes the following steps:

[0020] S211. Denoise the carbonized forming images in the sample set based on the multi-frame average denoising algorithm to obtain the denoised carbonized forming images;

[0021] Set the noisy image as shown in the formula:

[0022] g(x) = f(x) + n(x)

[0023] where g(x) is the noisy image, f(x) is the denoised image, and n(x) is the noise on the image;

[0024] Set the number of carbonization forming image frames as Z, and the carbonization forming image after multi-frame averaging is as shown in the formula:

[0025]

[0026] Among them, (i, j) represents the coordinate position of the pixel point, is the average gray value output at this point, g l (i, j) is the gray value of the l-th frame image at this position; f(i, j) is the gray value of the ideal noise-free image at this position, n l (i, j) is the gray value of the noise at this position in the l-th frame image;

[0027] Set the carbonization forming image after multi-frame averaging as the carbonization forming image after noise reduction;

[0028] S212. Stretch the carbonization forming image after noise reduction;

[0029] S213. Set the mapped carbonization forming image as the processed carbonization forming image.

[0030] Preferably, the stretching of the carbonization forming image after noise reduction includes the following steps:

[0031] For each frame of carbonization forming image X after logarithmic transformation, set two thresholds T min and T max , among which, for each frame of carbonization forming image, if the gray value x of its pixel is less than T min , make it equal to T min , and for each frame of carbonization forming image, if the gray value x of its pixel is greater than T max , make it equal to T max ;

[0032] Since the set image is 16-bit, each bit is represented by binary 0 and 1, and the maximum value that 16-bit binary can represent is 65535; so the gray values in the range of T max and T min will be mapped to between 0 and 65535;

[0033]

[0034] Among them, y is the mapped gray value, and Y is the output image.

[0035] Preferably, the processing of the parameter information of the corresponding carbonization forming image in the sample set to obtain the parameter information of the processed corresponding carbonization forming image includes the following steps:

[0036] Set the parameter information of the collected carbonization forming image to include: the temperature during the carbonization process and the pressure during the carbonization process;

[0037] Process the parameter information of the corresponding carbonization forming images in the sample set by means of linear regression;

[0038] Set the input parameter information as the temperature during the carbonization process and the pressure during the carbonization process;

[0039] Set the linear relationship between the temperature during the carbonization process and the pressure during the carbonization process as:

[0040] f = w×p + b;

[0041] Wherein, f represents the temperature during the carbonization process, p represents the pressure during the carbonization process, w represents the initial linear relationship weight, and b represents the bias value.

[0042] Through the method of separately processing the carbonization forming images in the sample set and the parameter information of the corresponding carbonization forming images, the processed carbonization forming images and the parameter information of the processed corresponding carbonization forming images are obtained, ensuring the accuracy of the co-forming control.

[0043] Preferably, the steps of collecting the scoring data of the processed carbonization forming images and the parameter information of the corresponding carbonization forming images and constructing a training set of the carbonization forming images and the parameter information of the corresponding carbonization forming images include the following:

[0044] S31. Collect the scoring data of the processed carbonization forming images and the parameter information of the corresponding carbonization forming images, and calculate the objective scores of each group of processed carbonization forming images and the parameter information of the corresponding carbonization forming images;

[0045] The objective score calculation formula is as follows:

[0046]

[0047] Wherein, represents the subjective score of the processed carbonization forming images and the parameter information of the corresponding carbonization forming images obtained by calculation, u m represents the scoring data of the m-th staff member, and M represents the number of staff members;

[0048] S32. Set the objective score threshold for calculation, and filter the processed carbonization forming images and the parameter information of the corresponding carbonization forming images based on the set objective score threshold;

[0049] Retain the processed carbonization forming images and the parameter information of the corresponding carbonization forming images that are greater than the objective score threshold, and remove the processed carbonization forming images and the parameter information of the corresponding carbonization forming images that are less than or equal to the objective score threshold;

[0050] Construct a training set of carbonization forming images and corresponding carbonization forming image parameter information based on the retained processed carbonization forming images and corresponding carbonization forming image parameter information.

[0051] The present invention ensures the accuracy of co-forming control by collecting scoring data of processed carbonization forming images and corresponding carbonization forming image parameter information, calculating the objective scores of each group of processed carbonization forming images and corresponding carbonization forming image parameter information, and filtering based on the calculated objective scores.

[0052] Preferably, optimizing the processed carbonization forming images and corresponding carbonization forming image parameter information in the training set based on the multi-objective genetic algorithm to obtain the optimal parameter information for carbonization forming includes the following steps:

[0053] S41. Set the population size and the number of iterations of the genetic algorithm;

[0054] S42. Perform population initialization and randomly generate an initial population S gen ;

[0055] S43. Take the linear relationship between the temperature during the carbonization process and the pressure during the carbonization process as the fitness function of the genetic algorithm, and calculate the fitness of each individual in the population;

[0056] Set each individual to represent a group of processed carbonization forming images and corresponding carbonization forming image parameter information;

[0057] The fitness calculation formula for each individual is as follows:

[0058]

[0059] Among them, Fit(q) represents the fitness of the qth individual, f represents the temperature during the carbonization process, and p represents the pressure during the carbonization process;

[0060] S44. Select excellent individuals from all individuals based on the roulette wheel method;

[0061] The formula for selecting excellent individuals from all individuals by the roulette wheel method is as follows:

[0062]

[0063] Among them, α(q) represents the probability that individual q is selected, and Q represents the population size;

[0064] S45. Cross the selected excellent individuals by the order crossover method, and a new population S' is generated after crossing gen ;

[0065] S46. Randomly select an individual in the population for mutation with a set probability to generate a mutated population S". gen ;

[0066] S47. Compare the fitness difference ΔFit between the initial population and the population after crossover and mutation by the genetic algorithm.

[0067] When ΔFit < 0, it means the fitness of the mutated population is higher than that of the initial population, and accept this population. When ΔFit ≥ 0, it means the fitness of the mutated population is lower than that of the initial population, and reject this population.

[0068] S48. Judge whether the maximum iteration number is reached according to the iteration number of the algorithm. When the maximum iteration number is reached, output the optimal solution. When the maximum iteration number is not reached, continue to execute steps S44 - S47.

[0069] Set the output optimal solution as the optimal parameter information for carbonization forming. The optimal parameter information includes the optimal carbonization forming image and the parameter information corresponding to the optimal carbonization forming image.

[0070] S5. Install a carbonization forming monitoring device to monitor the carbonization state and carbonization image data of the material in the current area in real time, and regulate the carbonization state of the material in the current area based on the obtained optimal parameter information for carbonization forming.

[0071] The present invention optimizes the processed carbonization forming images and the corresponding carbonization forming image parameter information in the training set by using a multi - objective genetic algorithm, and optimizes the carbonization forming images and the corresponding carbonization forming image parameter information by constructing a fitness function and continuously iterating, thereby improving the accuracy of intelligent collaborative forming control.

[0072] Preferably, the regulating the carbonization state of the material in the current area based on the obtained optimal parameter information for carbonization forming includes the following steps:

[0073] Set the temperature threshold during the carbonization process and the pressure threshold during the carbonization process based on the optimal parameter information for carbonization forming.

[0074] When the carbonization forming monitoring device monitors that the real - time temperature and pressure in the current area are less than the set thresholds, regulate by increasing the temperature and pressure in the current area.

[0075] When the carbonization forming monitoring device monitors that the real - time temperature and pressure in the current area are greater than the set thresholds, regulate by decreasing the temperature and pressure in the current area.

[0076] Observe whether the material in the current area is carbonized and formed by comparing the real - time monitored carbonization image data with the optimal carbonization forming image in the optimal parameter information.

[0077] The present invention installs a carbonization forming monitoring device to monitor the carbonization state and carbonization image data of materials in the current area in real time. At the same time, based on the obtained optimal parameter information of carbonization forming, it regulates the carbonization state of materials in the current area, ensuring the real-time nature of intelligent collaborative forming control.

[0078] Embodiment 2

[0079] This embodiment also discloses a multi-channel intelligent collaborative forming control system based on a carbonization device, including: a data acquisition module, a data processing module, a data filtering module, a carbonization parameter optimization module, and a carbonization parameter regulation module;

[0080] The data acquisition module is used to collect carbonization forming images and corresponding carbonization forming image parameter information;

[0081] The data processing module is used to process the collected carbonization forming images and corresponding carbonization forming image parameter information;

[0082] The data filtering module is used to filter the processed carbonization forming images and corresponding carbonization forming image parameter information;

[0083] The carbonization parameter optimization module is used to optimize the processed carbonization forming images and corresponding carbonization forming image parameter information, and output the optimal carbonization parameters;

[0084] The carbonization parameter regulation module is used to regulate according to the calculated optimal carbonization parameters.

[0085] (III) Beneficial effects

[0086] Compared with the prior art, the present invention provides a multi-channel intelligent collaborative forming control method and system based on a carbonization device, having the following beneficial effects:

[0087] 1. The invention collects carbonization forming images and corresponding carbonization forming image parameter information, constructs a carbonization forming data sample set, and at the same time processes the carbonization forming images and corresponding carbonization forming image parameter information in the sample set, and collects the scoring data of the processed carbonization forming images and corresponding carbonization forming image parameter information, constructs a training set of carbonization forming images and corresponding carbonization forming image parameter information. At the same time, it optimizes the data in the training set through a multi-objective genetic algorithm to obtain the optimal parameter information, and based on the obtained optimal parameter information of carbonization forming, it regulates the carbonization state of materials in the current area, improving the accuracy and real-time nature of intelligent collaborative forming control.

[0088] 2. The present invention obtains the processed carbonization forming image and the parameter information of the corresponding carbonization forming image by processing the carbonization forming image and the parameter information of the corresponding carbonization forming image in the sample set respectively, ensuring the accuracy of collaborative forming control.

[0089] 3. The present invention ensures the accuracy of collaborative forming control by collecting the scoring data of the processed carbonization forming image and the parameter information of the corresponding carbonization forming image, calculating the objective scores of each group of the processed carbonization forming image and the parameter information of the corresponding carbonization forming image, and filtering based on the calculated objective scores.

[0090] 4. The present invention optimizes the processed carbonization forming image and the parameter information of the corresponding carbonization forming image in the training set by using a multi-objective genetic algorithm, and optimizes the carbonization forming image and the parameter information of the corresponding carbonization forming image by constructing a fitness function and continuously iterating, improving the accuracy of intelligent collaborative forming control.

[0091] 5. The present invention installs carbonization forming monitoring equipment to monitor the carbonization state and carbonization image data of materials in the current area in real time, and at the same time regulates the carbonization state of materials in the current area based on the obtained optimal parameter information of carbonization forming, ensuring the real-time performance of intelligent collaborative forming control. Description of the Drawings

[0092] Figure 1 It is a schematic structural diagram of the multi-channel intelligent collaborative forming control process of the carbonization equipment of the present invention; Detailed Embodiments

[0093] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0094] Embodiment 1

[0095] This embodiment discloses a multi-channel intelligent collaborative forming control method based on a carbonization device, specifically including the following steps:

[0096] S1. Collect the carbonization forming image and the parameter information of the corresponding carbonization forming image, and construct a carbonization forming data sample set;

[0097] S2. Process the carbonization forming image and the parameter information of the corresponding carbonization forming image in the sample set to obtain the processed carbonization forming image and the parameter information of the corresponding carbonization forming image;

[0098] Processing the carbonization forming images and the parameter information corresponding to the carbonization forming images in the sample set to obtain the processed carbonization forming images and the parameter information corresponding to the carbonization forming images includes the following steps:

[0099] S21. Process the carbonization forming images in the sample set to obtain the processed carbonization forming images;

[0100] S211. Denoise the carbonization forming images in the sample set based on the multi-frame average denoising algorithm to obtain the denoised carbonization forming images;

[0101] Set the noisy image as shown in the formula:

[0102] g(x) = f(x) + n(x)

[0103] where g(x) is the noisy image, f(x) is the denoised image, and n(x) is the noise on the image;

[0104] Set the number of frames of the carbonization forming images as Z, and the carbonization forming images after multi-frame averaging are as shown in the formula:

[0105]

[0106] where (i, j) represents the coordinate position of the pixel point, is the average gray value output at this point, g l (i, j) is the gray value of the l-th frame image at this position; f(i, j) is the gray value of the ideal noise-free image at this position, n l (i, j) is the gray value of the noise at this position in the l-th frame image;

[0107] Set the carbonization forming images after multi-frame averaging as the denoised carbonization forming images;

[0108] S212. Stretch the denoised carbonization forming images;

[0109] Perform logarithmic transformation on each frame of the denoised carbonization forming image X;

[0110] Set the function of the logarithmic transformation as:

[0111] h = clog(1 + r) r ∈ [0, 1]

[0112] where h is the gray value of the pixel point after transformation, c is a constant, and r is the gray value range of each frame of the carbonization forming image X;

[0113] S212. Map each frame of the carbonization forming image after logarithmic transformation to obtain the mapped carbonization forming images;

[0114] For each frame of carbonized forming image X after logarithmic transformation, set two thresholds T min and T max based on its gray value. For each frame of carbonized forming image, if the gray value x of its pixel is less than T min , make it equal to T min . For each frame of carbonized forming image, if the gray value x of its pixel is greater than T max , make it equal to T max ;

[0115] Since the set image is 16-bit, each bit is represented by binary 0 and 1, and the maximum value that 16-bit binary can represent is 65535. Therefore, the gray values in the range of T max and T min will be mapped to the range of 0 to 65535;

[0116]

[0117] where y is the mapped gray value and Y is the output image;

[0118] S213. Set the mapped carbonized forming image as the processed carbonized forming image;

[0119] S22. Process the parameter information of the corresponding carbonized forming image in the sample set to obtain the processed parameter information of the corresponding carbonized forming image;

[0120] Set the parameter information of the collected carbonized forming image to include: the temperature during the carbonization process and the pressure during the carbonization process;

[0121] Process the parameter information of the corresponding carbonized forming image in the sample set by linear regression;

[0122] Set the input parameter information to be the temperature during the carbonization process and the pressure during the carbonization process;

[0123] Set the linear relationship between the temperature during the carbonization process and the pressure during the carbonization process to be:

[0124] f = w × p + b;

[0125] where f represents the temperature during the carbonization process, p represents the pressure during the carbonization process, w represents the initial linear relationship weight, and b represents the bias value;

[0126] S3. Collect the scoring data of the processed carbonized forming image and the parameter information of the corresponding carbonized forming image, and construct a training set of the carbonized forming image and the parameter information of the corresponding carbonized forming image;

[0127] S31. Collect the scoring data of the processed carbonized forming images and the corresponding carbonized forming image parameter information, and calculate the objective scores of each group of processed carbonized forming images and the corresponding carbonized forming image parameter information;

[0128] The objective score calculation formula is as follows:

[0129]

[0130] where, represents the subjective score of the processed carbonized forming image and the corresponding carbonized forming image parameter information obtained by calculation, and u m represents the scoring data of the m-th staff member, and M represents the number of staff members;

[0131] S32. Set the calculated objective score threshold, and filter the processed carbonized forming images and the corresponding carbonized forming image parameter information based on the set objective score threshold;

[0132] Retain the processed carbonized forming images and the corresponding carbonized forming image parameter information greater than the objective score threshold, and remove the processed carbonized forming images and the corresponding carbonized forming image parameter information less than or equal to the objective score threshold;

[0133] Based on the retained processed carbonized forming images and the corresponding carbonized forming image parameter information, construct a training set of carbonized forming images and the corresponding carbonized forming image parameter information;

[0134] S4. Optimize the processed carbonized forming images and the corresponding carbonized forming image parameter information in the training set based on the multi-objective genetic algorithm to obtain the optimal parameter information of carbonized forming, including the following steps:

[0135] S41. Set the population size and the number of iterations of the genetic algorithm;

[0136] S42. Perform population initialization and randomly generate the initial population S gen ;

[0137] S43. Take the linear relationship between the temperature during the carbonization process and the pressure during the carbonization process as the fitness function of the genetic algorithm, and calculate the fitness of each individual in the population;

[0138] Set each individual to represent a group of processed carbonized forming images and the corresponding carbonized forming image parameter information;

[0139] The fitness calculation formula of each individual is as follows:

[0140]

[0141] Among them, Fit(q) represents the fitness of the q-th individual, f represents the temperature during the carbonization process, and p represents the pressure during the carbonization process;

[0142] S44. Select excellent individuals from all individuals based on the roulette wheel method;

[0143] The calculation formula for selecting excellent individuals from all individuals by the roulette wheel method is as follows:

[0144]

[0145] Among them, α(q) represents the probability that individual q is selected, and Q represents the population size;

[0146] S45. Cross the selected excellent individuals by the order crossover method, and a new population S' is generated after crossing gen ;

[0147] S46. Randomly select an individual in the population to perform mutation with a set probability, and generate a mutated population S gen ;

[0148] S47. Compare the fitness difference ΔFit between the initial population and the population after genetic algorithm crossover and mutation;

[0149] When ΔFit < 0, it means that the fitness of the mutated population is higher than that of the initial population, and accept this population. When ΔFit ≥ 0, it means that the fitness of the mutated population is lower than that of the initial population, and reject this population;

[0150] S48. Judge whether the maximum number of iterations is reached according to the number of iterations of the algorithm. When the maximum number of iterations is reached, output the optimal solution. When the maximum number of iterations is not reached, continue to execute steps S44 - S47;

[0151] Set the output optimal solution as the optimal parameter information for carbonization forming. The optimal parameter information includes the optimal carbonization forming image and the parameter information corresponding to the optimal carbonization forming image;

[0152] S5. Install a carbonization forming monitoring device to monitor the carbonization state and carbonization image data of the material in the current area in real time, and regulate the carbonization state of the material in the current area based on the obtained optimal parameter information for carbonization forming;

[0153] Regulating the carbonization state of the material in the current area based on the obtained optimal parameter information for carbonization forming includes the following steps:

[0154] Set the temperature threshold during the carbonization process and the pressure threshold during the carbonization process based on the optimal parameter information for carbonization forming;

[0155] When the carbonization forming monitoring device monitors that the real-time temperature and pressure in the current area are less than the set threshold, it is adjusted by increasing the temperature and pressure in the current area;

[0156] When the carbonization forming monitoring device monitors that the real-time temperature and pressure in the current area are greater than the set threshold, it is adjusted by decreasing the temperature and pressure in the current area;

[0157] Furthermore, by comparing the real-time monitored carbonization image data with the optimal carbonization forming image in the optimal parameter information, it is observed whether the material in the current area is carbonized and formed;

[0158] Embodiment 2

[0159] This embodiment also discloses a multi-channel intelligent collaborative forming control system based on a carbonization device, including: a data acquisition module, a data processing module, a data filtering module, a carbonization parameter optimization module, and a carbonization parameter regulation module;

[0160] The data acquisition module is used to collect carbonization forming images and corresponding carbonization forming image parameter information;

[0161] The data processing module is used to process the collected carbonization forming images and corresponding carbonization forming image parameter information;

[0162] The data filtering module is used to filter the processed carbonization forming images and corresponding carbonization forming image parameter information;

[0163] The carbonization parameter optimization module is used to optimize the processed carbonization forming images and corresponding carbonization forming image parameter information, and output the optimal carbonization parameters;

[0164] The carbonization parameter regulation module is used to regulate according to the calculated optimal carbonization parameters.

[0165] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A multi-channel intelligent collaborative forming control method based on carbonization equipment, characterized in that: The following steps are involved: S1, collecting carbonization forming images and parameter information corresponding to the carbonization forming images, and constructing a carbonization forming data sample set; S2, processing the carbonization forming images and the parameter information corresponding to the carbonization forming images in the sample set to obtain the processed carbonization forming images and the parameter information corresponding to the carbonization forming images; S3, collecting the processed carbonization forming images and the scoring data of the corresponding carbonization forming image parameter information, and constructing a training set of the carbonization forming images and the corresponding carbonization forming image parameter information; S4, optimizing the processed carbonization forming images and corresponding carbonization forming image parameter information in the training set based on a multi-objective genetic algorithm to obtain optimal parameter information for carbonization forming; S5. Install carbonization forming monitoring equipment to monitor the carbonization state and carbonization image data of the material in the current area in real time, and adjust the carbonization state of the material in the current area based on the obtained optimal parameter information of carbonization forming.

2. According to claim 1, a multi-channel intelligent collaborative forming control method based on carbonization equipment is characterized in that: The processing of the carbonization forming images and the parameter information corresponding to the carbonization forming images in the sample set includes the following steps: S21, processing the carbonization forming images in the sample set to obtain processed carbonization forming images; S22, processing the parameter information corresponding to the carbonization forming image in the sample set to obtain the processed parameter information corresponding to the carbonization forming image.

3. A multi-channel intelligent collaborative forming control method based on carbonization equipment according to claim 2, characterized in that: The processing of the carbonization forming images in the sample set to obtain the processed carbonization forming images comprises the following steps: S211, performing noise reduction on the carbonization forming images in the sample set based on a multi-frame average noise reduction algorithm to obtain a noise-reduced carbonization forming image; Set the noisy image as shown in the formula: g(x)=f(x)+n(x) Among them, g(x) is the noisy image, f(x) is the denoised image, and n(x) is the noise on the image; The number of carbonization forming image frames is set to Z, and the carbonization forming image after multi-frame averaging is shown in the formula: Among them, (i, j) represents the coordinate position of the pixel point, is the grayscale mean value output at this point, g l (i, j) is the gray value of the l-th frame image at this position; f(i, j) is the gray value of the ideal noise-free image at this position, n l (i, j) is the gray value of the noise at this position in the l-th frame image; The carbonized forming image after multi-frame averaging is set as the carbonized forming image after noise reduction; S212, stretching the carbonized formed image after noise reduction; S213, setting the mapped carbonization forming image as the processed carbonization forming image.

4. The multi-channel intelligent collaborative forming control method based on carbonization equipment according to claim 3 is characterized in that: The stretching of the carbonized formed image after noise reduction comprises the following steps: For each frame of carbonized image X after logarithmic transformation, two thresholds T are set based on its gray value. min and T max , where the gray value x of each pixel of the carbonization forming image is less than T min Let it be equal to T min , the gray value x of each pixel in the carbonization forming image is greater than T max Let it be equal to T max ; Since the image is set to 16 bits, each bit is represented by binary 0 and 1, and the maximum value that 16 bits of binary can represent is 65535; so T max and T min The grayscale values ​​within the interval will be mapped to between 0 and 65535; Among them, y is the gray value after mapping, and Y is the output image.

5. The multi-channel intelligent collaborative forming control method based on carbonization equipment according to claim 2 is characterized in that: The step of processing the parameter information of the corresponding carbonization forming image in the sample set to obtain the processed parameter information of the corresponding carbonization forming image comprises the following steps: Setting the parameter information of the collected carbonization forming image includes: the temperature during the carbonization process and the pressure during the carbonization process; The parameter information of the corresponding carbonization forming images in the sample set is processed by linear regression; The input parameter information is set to be the temperature during the carbonization process and the pressure during the carbonization process; The linear relationship between the temperature during the carbonization process and the pressure during the carbonization process is set to: f = w × p + b; Among them, f represents the temperature during the carbonization process, p represents the pressure during the carbonization process, w represents the initial linear relationship weight, and b represents the bias value.

6. The multi-channel intelligent collaborative forming control method based on carbonization equipment according to claim 1 is characterized in that: The step of collecting the processed carbonization forming images and the scoring data of the corresponding carbonization forming image parameter information and constructing a training set of the carbonization forming images and the corresponding carbonization forming image parameter information comprises the following steps: S31, collecting the scoring data of the processed carbonization forming images and the corresponding carbonization forming image parameter information, and calculating the objective score of each group of processed carbonization forming images and the corresponding carbonization forming image parameter information; The objective score calculation formula is as follows: in, represents the calculated subjective score of the processed carbonization forming image and the corresponding carbonization forming image parameter information, u m represents the score data of the mth staff member, and M represents the number of staff members; S32, setting a calculated objective score threshold, and filtering the processed carbonization forming image and corresponding carbonization forming image parameter information based on the set objective score threshold; retaining the processed carbonized forming images and corresponding carbonized forming image parameter information that are greater than the objective score threshold, and removing the processed carbonized forming images and corresponding carbonized forming image parameter information that are less than or equal to the objective score threshold; Based on the retained processed carbonization forming images and the corresponding carbonization forming image parameter information, a training set of carbonization forming images and the corresponding carbonization forming image parameter information is constructed.

7. The multi-channel intelligent collaborative forming control method based on carbonization equipment according to claim 1 is characterized in that: The method of optimizing the processed carbonization forming images and the corresponding carbonization forming image parameter information in the training set based on the multi-objective genetic algorithm to obtain the optimal parameter information of the carbonization forming includes the following steps: S41, set the genetic population size and number of iterations; S42, initialize the population and randomly generate the initial population S gen ; S43, using the linear relationship between the temperature during the carbonization process and the pressure during the carbonization process as the fitness function of the genetic algorithm, and calculating the fitness of each individual in the population; Each individual is set to represent a set of processed carbonization forming images and corresponding carbonization forming image parameter information; The fitness calculation formula for each individual is as follows: Among them, Fit(q) represents the fitness of the qth individual, f represents the temperature during the carbonization process, and p represents the pressure during the carbonization process; S44, selecting the best individuals from all individuals based on the roulette wheel method; The calculation formula for selecting the best individuals among all individuals by roulette is as follows: Among them, α(q) represents the probability of individual q being selected, and Q represents the population size; S45, cross the selected excellent individuals by sequential crossover, and generate a new population S' after crossover gen ; S46, randomly select an individual in the population to perform marginalization with a set probability, and generate a mutated population S" gen ; S47, comparing the fitness difference ΔFit between the initial population and the population after crossover mutation by the genetic algorithm; When ΔFit<0, it means that the fitness of the mutated population is higher than that of the initial population, and the population is accepted. When ΔFit≥0, it means that the fitness of the mutated population is lower than that of the initial population, and the population is rejected. S48, judging whether the maximum number of iterations has been reached according to the number of iterations of the algorithm, outputting the optimal solution when the maximum number of iterations has been reached, and continuing to execute steps S44-S47 when the maximum number of iterations has not been reached; The optimal solution output is set as the optimal parameter information of carbonization forming, and the optimal parameter information includes the optimal carbonization forming image and parameter information corresponding to the optimal carbonization forming image.

8. The multi-channel intelligent collaborative forming control method based on carbonization equipment according to claim 1 is characterized in that: The step of regulating the carbonization state of the material in the current region based on the obtained optimal parameter information of carbonization forming comprises the following steps: The carbonization state of the material in the current area is regulated based on the obtained optimal parameter information of carbonization forming, including the following steps: Setting a temperature threshold during the carbonization process and a pressure threshold during the carbonization process based on the optimal parameter information of the carbonization forming; When the carbonization forming monitoring device detects that the real-time temperature and pressure in the current area are lower than the set threshold, the temperature and pressure in the current area are increased to control the temperature; When the carbonization forming monitoring device detects that the real-time temperature and pressure in the current area are greater than the set threshold, the temperature and pressure in the current area are lowered to control the temperature; By comparing the real-time monitoring carbonization image data with the optimal carbonization forming image in the optimal parameter information, it is observed whether the material in the current area is carbonized.

9. A system for implementing the multi-channel intelligent collaborative forming control method based on carbonization equipment according to any one of claims 1 to 8, characterized in that: include: Data acquisition module, data processing module, data filtering module, carbonization parameter optimization module and carbonization parameter control module; The data acquisition module is used to collect the carbonization forming image and the corresponding carbonization forming image parameter information; The data processing module is used to process the collected carbonization forming images and corresponding carbonization forming image parameter information; The data filtering module is used to filter the processed carbonization forming image and the corresponding carbonization forming image parameter information; The carbonization parameter optimization module is used to optimize the processed carbonization forming image and the corresponding carbonization forming image parameter information, and output the optimal carbonization parameters; The carbonization parameter control module is used to control the optimal carbonization parameters obtained by calculation.

Images