An online detection method, system and medium for processing of a polymer composite material

Abstract

The present application relates to the technical field of high polymer composite material processing, and particularly relates to an online detection method and system for high polymer composite material processing and a medium, the method comprising: controlling a hot-press forming device to hot-press form mixed and uniform high polymer composite material to obtain a high polymer composite material sample to be detected; controlling a detection device installed at an outlet end of the hot-press forming device to sequentially perform rheological property detection and optical property detection on the high polymer composite material sample to obtain rheological property data and an infrared spectrum; wherein the rheological property data comprises at least one of viscosity, elastic modulus and yield stress; determining a performance parameter of the high polymer composite material sample based on the rheological property data and the infrared spectrum; determining an adjustment parameter based on the performance parameter and a preset standard parameter, and adjusting the hot-press forming device based on the adjustment parameter; and the present application can adjust process parameters in real time and improve processing efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of polymer material processing, and in particular to an online detection method, system and medium for polymer composite material processing. BACKGROUND

[0002] In the conventional polymer composite material processing process, an offline detection method is usually used to detect the processing result. This method needs to take out a little of the composite material in the molding process and send it to the detection instrument for offline detection. However, this detection method has the problems of time delay and sample representativeness. Because sampling causes time delay, the obtained sample cannot completely represent the real-time material morphology. In addition, offline detection cannot adjust the process parameters in real time, resulting in low processing efficiency. Therefore, there is an urgent need for a method that can detect polymer composite materials in real time and adjust process parameters. SUMMARY

[0003] The present application aims to provide an online detection method, system and medium for polymer composite material processing to solve at least one technical problem in the background art.

[0004] In order to achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0005] In a first aspect, the present application provides an online detection method for polymer composite material processing, which comprises the following steps:

[0006] S100, controlling a hot press molding device to hot press mold the mixed and uniform polymer composite material to obtain a polymer composite material sample to be detected;

[0007] S200, controlling a detection device installed at the outlet end of the hot press molding device to sequentially perform rheological property detection and optical property detection on the polymer composite material sample to obtain rheological property data and an infrared spectrum; wherein the rheological property data includes at least one of viscosity, elastic modulus and yield stress;

[0008] S300, determining a performance parameter of the polymer composite material sample based on the rheological property data and the infrared spectrum;

[0009] S400, determining an adjustment parameter based on the performance parameter and a preset standard parameter, and adjusting the hot press molding device based on the adjustment parameter.

[0010] Optionally, in S200, the control of the detection device installed at the outlet end of the hot press molding device on the polymer composite material sample to sequentially perform rheological property detection and optical property detection to obtain rheological property data and an infrared spectrum comprises:

[0011] S210, Set test conditions, including material type, temperature, pressure and duration;

[0012] S220, Start the rheometer according to the test conditions to conduct the test, and record the rheological performance data of the material during the test. The rheological performance data includes viscosity, elastic modulus and yield stress.

[0013] S230: After completing the rheological property test, the material is sent to an infrared spectrometer for infrared spectral detection and the infrared spectrum is recorded.

[0014] Optionally, in S300, determining the performance parameters of the polymer composite material sample based on the rheological property data and infrared spectrum includes:

[0015] S310 acquires multiple infrared spectra, each infrared spectra corresponding to multiple sets of rheological performance data. Multiple sets of multimodal data are formed from the infrared spectra and rheological performance data. Performance scores are performed on each set of multimodal data, and each performance score corresponds to a performance parameter, resulting in multiple sets of training data, which serve as the training set.

[0016] S320, Establish a multimodal deep learning model, and use the multimodal deep learning model to train the multiple sets of training data to obtain a trained model;

[0017] S330, input the rheological performance data and infrared spectrum into the trained model to obtain the performance parameters of the polymer composite material sample.

[0018] Optionally, in S320, the step of using the multimodal deep learning model to train the multiple sets of training data to obtain a trained model includes:

[0019] S321, Initialize the parameters of the multimodal deep learning model using a random method;

[0020] S322: Input a set of training data into a multimodal deep learning model and calculate the error between the model output and the expected result;

[0021] S323, Adjust the model parameters based on the error, and evaluate the model's performance using any set of remaining training data, the performance including accuracy, recall, and F1 score;

[0022] S324, After each iteration, the hyperparameters are adjusted according to the performance changes of the model. The hyperparameters include the learning rate, batch size, and number of iterations.

[0023] S325, Repeat steps S322 to S324 until the model's performance reaches the preset value or the number of iterations reaches the preset value, and the trained model is obtained.

[0024] Optionally, in S330, inputting the rheological property data and infrared spectrum into the trained model to obtain the performance parameters of the polymer composite sample includes:

[0025] S331, Input the rheological performance data and infrared spectrum into the trained model to obtain a performance score;

[0026] S332, determine the performance parameters of the polymer composite material sample based on the performance score.

[0027] Optionally, in S400, determining the adjustment parameters based on the performance parameters and preset standard parameters, and adjusting the hot pressing equipment based on the adjustment parameters, includes:

[0028] S410, compare the performance parameters with preset standard parameters;

[0029] S420, determine the adjustment parameters based on the comparison results;

[0030] S430, adjust the process parameters of the hot pressing molding equipment according to the adjustment parameters.

[0031] Optionally, in S430, adjusting the process parameters of the hot pressing molding equipment according to the adjustment parameters includes:

[0032] Adjust the temperature, pressure, or duration of the hot press molding equipment.

[0033] Secondly, embodiments of the present invention provide an online detection system for the processing of polymer composite materials, the system comprising:

[0034] Hot pressing equipment is used to hot press uniformly mixed polymer composite materials to obtain polymer composite material samples to be tested.

[0035] The testing equipment is installed at the outlet of the hot pressing molding equipment and is used to sequentially test the rheological properties and optical properties of polymer composite material samples to obtain rheological property data and infrared spectra.

[0036] Control system, including:

[0037] At least one processor;

[0038] At least one memory for storing at least one program;

[0039] When the at least one program is executed by the at least one processor, the at least one processor implements the online detection method for polymer composite material processing as described in any of the preceding claims.

[0040] Thirdly, embodiments of the present invention provide a computer-readable storage medium storing a processor-executable program, characterized in that the processor-executable program, when executed by a processor, is used to perform an online detection method for processing polymer composite materials as described in any of the preceding claims.

[0041] The beneficial effects of this invention are as follows: This invention discloses an online detection method, system, and medium for processing polymer composite materials. This invention solves the problems of time delay and sample representativeness in offline detection, improving detection efficiency and accuracy. Through the online detection method, process parameters can be adjusted in real time, improving processing efficiency. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a framework diagram of the online detection method for polymer composite material processing in this embodiment of the invention;

[0044] Figure 2 This is a schematic diagram of the online detection system for polymer composite material processing in an embodiment of the present invention. Detailed Implementation

[0045] The following will provide a clear and complete description of the concept, specific structure, and technical effects of the present invention in conjunction with embodiments and accompanying drawings, so as to fully understand the purpose, solution, and effects of the present invention. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of the present invention can be combined with each other.

[0046] See Figure 1 , Figure 1 This invention provides an online detection method for the processing of polymer composite materials, the method comprising the following steps:

[0047] S100, control the hot pressing molding equipment to hot press the uniformly mixed polymer composite material to obtain the polymer composite material sample to be tested;

[0048] S200, the detection equipment installed at the outlet of the hot pressing molding equipment is controlled to perform rheological property testing and optical property testing on the polymer composite material sample in sequence, so as to obtain rheological property data and infrared spectrum; wherein, the rheological property data includes at least one of viscosity, elastic modulus and yield stress;

[0049] S300, Based on the rheological performance data and infrared spectrum, determine the performance parameters of the polymer composite material sample;

[0050] S400, based on the performance parameters and preset standard parameters, determine the adjustment parameters, and adjust the hot pressing molding equipment based on the adjustment parameters.

[0051] This invention provides an online detection method, system, and medium for processing polymer composite materials, solving the problems of time delay and sample representativeness in offline detection, and improving detection efficiency and accuracy. The online detection method allows for real-time adjustment of process parameters, thereby improving processing efficiency.

[0052] In some preferred embodiments, in S200, the control device installed at the outlet of the hot pressing molding equipment sequentially performs rheological property testing and optical property testing on the polymer composite material sample to obtain rheological property data and infrared spectra, including:

[0053] S210, Set test conditions, including material type, temperature, pressure and duration;

[0054] S220, Start the rheometer according to the test conditions to conduct the test, and record the rheological performance data of the material during the test. The rheological performance data includes viscosity, elastic modulus and yield stress.

[0055] S230: After completing the rheological property test, the material is sent to an infrared spectrometer for infrared spectral detection and the infrared spectrum is recorded.

[0056] By following the steps above, the performance parameters of polymer composite material samples can be obtained more accurately, thereby better guiding the adjustment of the processing procedure.

[0057] In some preferred embodiments, in step S300, determining the performance parameters of the polymer composite material sample based on the rheological property data and infrared spectrum includes:

[0058] S310 acquires multiple infrared spectra, each infrared spectra corresponding to multiple sets of rheological performance data. Multiple sets of multimodal data are formed from the infrared spectra and rheological performance data. Performance scores are performed on each set of multimodal data, and each performance score corresponds to a performance parameter, resulting in multiple sets of training data, which serve as the training set.

[0059] S320, Establish a multimodal deep learning model, and use the multimodal deep learning model to train the multiple sets of training data to obtain a trained model;

[0060] S330, input the rheological performance data and infrared spectrum into the trained model to obtain the performance parameters of the polymer composite material sample.

[0061] By following the steps above, the performance parameters of polymer composite material samples can be determined more accurately, further improving detection efficiency and accuracy. Using multimodal deep learning models, features and correlations within multimodal data can be better extracted, leading to a more accurate assessment of material performance.

[0062] In some preferred embodiments, in step S320, training the multiple sets of training data using the multimodal deep learning model to obtain a trained model includes:

[0063] S321, Initialize the parameters of the multimodal deep learning model using a random method;

[0064] S322: Input a set of training data into a multimodal deep learning model and calculate the error between the model output and the expected result;

[0065] S323, Adjust the model parameters based on the error, and evaluate the model's performance using any set of remaining training data, the performance including accuracy, recall, and F1 score;

[0066] S324, After each iteration, the hyperparameters are adjusted according to the performance changes of the model. The hyperparameters include the learning rate, batch size, and number of iterations.

[0067] S325, Repeat steps S322 to S324 until the model's performance reaches the preset value or the number of iterations reaches the preset value, and the trained model is obtained.

[0068] Adjusting the learning rate based on performance is as follows: If performance is poor, decrease the learning rate; if performance is good, increase the learning rate. If performance is poor, decrease the batch size; if performance is good, increase the batch size. If performance is poor, increase the number of iterations; if performance is good, decrease the number of iterations.

[0069] By following the steps above, a trained multimodal deep learning model can be obtained, which can be used for tasks such as classification, regression, and clustering on new input data. In practical applications, appropriate multimodal deep learning models and hyperparameter tuning methods can be selected based on the specific task requirements and data characteristics to achieve better performance and results.

[0070] In some preferred embodiments, in step S330, inputting the rheological property data and infrared spectrum into the trained model to obtain the performance parameters of the polymer composite material sample includes:

[0071] S331, Input the rheological performance data and infrared spectrum into the trained model to obtain a performance score;

[0072] S332, determine the performance parameters of the polymer composite material sample based on the performance score.

[0073] Through the above steps, the performance of new polymer composite material samples can be evaluated using a trained multimodal deep learning model, and process optimization or quality assessment can be performed based on the evaluation results.

[0074] In some preferred embodiments, in step S400, determining adjustment parameters based on the performance parameters and preset standard parameters, and adjusting the hot pressing equipment based on the adjustment parameters, includes:

[0075] S410, compare the performance parameters with preset standard parameters;

[0076] S420, determine the adjustment parameters based on the comparison results;

[0077] S430, the adjustment parameters are used to adjust the process parameters of the hot pressing molding equipment.

[0078] By using the above steps, the process parameters of the hot pressing molding equipment can be adjusted in real time by comparing the performance parameters with the preset standard parameters, thereby achieving optimized control of the polymer composite material processing process.

[0079] The online detection method, system, and medium of this invention enable real-time monitoring and adjustment of the processing of polymer composite materials, improving processing efficiency and product quality. Simultaneously, training multiple sets of multimodal data using a multimodal deep learning model yields more accurate performance evaluation results, providing a basis for process optimization and quality assessment.

[0080] and Figure 1 The corresponding method is referenced. Figure 2 This invention provides an online detection system for polymer composite material processing, comprising:

[0081] Hot pressing equipment is used to hot press uniformly mixed polymer composite materials to obtain polymer composite material samples to be tested.

[0082] The testing equipment is installed at the outlet of the hot pressing molding equipment and is used to sequentially test the rheological properties and optical properties of polymer composite material samples to obtain rheological property data and infrared spectra.

[0083] Control system, including:

[0084] At least one processor;

[0085] At least one memory for storing at least one program;

[0086] When the at least one program is executed by the at least one processor, the at least one processor implements the online detection method for polymer composite material processing as described in any of the preceding claims.

[0087] It is evident that the content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0088] Furthermore, embodiments of the present invention also disclose a computer program product or computer program stored in a computer-readable storage medium. A processor of a computer device can read the computer program from the computer-readable storage medium, and the processor executes the computer program, causing the computer device to perform the described method. Similarly, the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0089] It will be understood by those skilled in the art that all or some of the methods and systems disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0090] The above is a detailed description of the preferred embodiments of this disclosure. However, this disclosure is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this disclosure. All such equivalent modifications or substitutions are included within the scope defined by the claims of this disclosure.

Claims

1. An online detection method for processing polymer composite materials, characterized in that, The method includes the following steps: S100, control the hot pressing molding equipment to hot press the uniformly mixed polymer composite material to obtain the polymer composite material sample to be tested; S200 controls the testing equipment installed at the outlet of the hot press molding equipment to sequentially perform rheological and optical property tests on the polymer composite material sample, obtaining rheological property data and infrared spectra, including: S210, Set test conditions, including material type, temperature, pressure and duration; S220, Start the rheometer according to the test conditions to conduct the test, and record the rheological performance data of the material during the test. The rheological performance data includes viscosity, elastic modulus and yield stress. S230: After completing the rheological property test, the material is sent to an infrared spectrometer for infrared spectral detection and the infrared spectrum is recorded. S300, based on the rheological property data and infrared spectrum, determine the performance parameters of the polymer composite material sample, including: S310 acquires multiple infrared spectra, each infrared spectra corresponding to multiple sets of rheological performance data. Multiple sets of multimodal data are formed from the infrared spectra and rheological performance data. Performance scores are performed on each set of multimodal data, and each performance score corresponds to a performance parameter, resulting in multiple sets of training data, which serve as the training set. S320, Establish a multimodal deep learning model, and use the multimodal deep learning model to train the multiple sets of training data to obtain a trained model; S330, Input the rheological performance data and infrared spectrum into the trained model to obtain the performance parameters of the polymer composite material sample; S400, based on the performance parameters and preset standard parameters, determine the adjustment parameters, and adjust the hot pressing molding equipment based on the adjustment parameters.

2. The online detection method for processing polymer composite materials according to claim 1, characterized in that, In S320, the step of using the multimodal deep learning model to train the multiple sets of training data to obtain a trained model includes: S321, Initialize the parameters of the multimodal deep learning model using a random method; S322: Input a set of training data into a multimodal deep learning model and calculate the error between the model output and the expected result; S323, Adjust the model parameters based on the error, and evaluate the model's performance using any set of remaining training data, the performance including accuracy, recall, and F1 score; S324, After each iteration, the hyperparameters are adjusted according to the performance changes of the model. The hyperparameters include the learning rate, batch size, and number of iterations. S325, Repeat steps S322 to S324 until the model's performance reaches the preset value or the number of iterations reaches the preset value, and the trained model is obtained.

3. The online detection method for processing polymer composite materials according to claim 2, characterized in that, In S330, the step of inputting the rheological property data and infrared spectrum into the trained model to obtain the performance parameters of the polymer composite material sample includes: S331, Input the rheological performance data and infrared spectrum into the trained model to obtain a performance score; S332, determine the performance parameters of the polymer composite material sample based on the performance score.

4. The online detection method for processing polymer composite materials according to claim 1, characterized in that, In S400, determining adjustment parameters based on the performance parameters and preset standard parameters, and adjusting the hot pressing molding equipment based on the adjustment parameters, includes: S410, compare the performance parameters with preset standard parameters; S420, determine the adjustment parameters based on the comparison results; S430, adjust the process parameters of the hot pressing molding equipment according to the adjustment parameters.

5. The online detection method for processing polymer composite materials according to claim 4, characterized in that, In S430, adjusting the process parameters of the hot pressing molding equipment according to the adjustment parameters includes: Adjust the temperature, pressure, or duration of the hot press molding equipment.

6. An online detection system for processing polymer composite materials, characterized in that, The system includes: Hot pressing equipment is used to hot press uniformly mixed polymer composite materials to obtain polymer composite material samples to be tested; The testing equipment is installed at the outlet of the hot pressing molding equipment and is used to sequentially test the rheological properties and optical properties of polymer composite material samples to obtain rheological property data and infrared spectra. Control system, including: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the online detection method for processing polymer composite materials as described in any one of claims 1 to 5.

7. A computer-readable storage medium storing a processor-executable program, characterized in that, The processor-executable program, when executed by the processor, is used to perform the method as described in any one of claims 1 to 5.

Images