Glass transition temperature testing method and apparatus, and device, medium and program product

Abstract

Disclosed in the present application are a glass transition temperature testing method and apparatus, and a device, a medium and a program product. The method comprises: respectively performing near-infrared spectroscopy tests on a plurality of standard samples in a target environment under a plurality of preset conditions, so as to obtain a near-infrared spectroscopy signal of each standard sample under each preset condition; acquiring a calibrated glass transition temperature of a target polymer in each standard sample; respectively creating training samples from the near-infrared spectroscopy signal, which corresponds to each standard sample under each preset condition, and the corresponding calibrated glass transition temperature, so as to obtain a training sample set; inputting the training sample set into a glass transition temperature measurement model, so as to obtain a measured glass transition temperature corresponding to each training sample; and on the basis of the measured glass transition temperature which correspond to each training sample, and the calibrated glass transition temperature, performing iterative training, so as to obtain a trained glass transition temperature measurement model. The present application can realize rapid and accurate measurement of a glass transition temperature at an industrial production site.

Description

Glass transition temperature testing methods, apparatus, equipment, media and procedures products

[0001] Cross-references to related applications

[0002] This application claims priority to Chinese Patent Application No. 202411612384.2, filed on November 12, 2024, entitled “Method, Apparatus, Equipment, Media and Procedure for Testing Glass Transition Temperature”, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application belongs to the field of glass transition temperature testing technology, and particularly relates to a glass transition temperature testing method, apparatus, equipment, computer storage medium, and computer program product. Background Technology

[0004] The glass transition temperature (Tg) is a key parameter characterizing the unique physical behavior of polymer materials. It marks the critical point at which polymer chains gain sufficient energy from a frozen glassy state to begin random rotation. At this specific temperature (Tg), the material undergoes a fundamental transformation from a hard and brittle glassy state to a soft and flowable rubbery state (or viscoelastic state), resulting in significant changes in its mechanical properties, such as elastic modulus and toughness. Therefore, the glass transition temperature is not only an important basis for determining the operating temperature range of polymer materials but also a core indicator for evaluating material processing performance and finished product quality. It holds immense significance in the fields of materials science and engineering, directly impacting product design, material selection, and the optimization and control of manufacturing processes.

[0005] Currently, the commonly used methods for measuring glass transition temperature in industrial production are differential scanning calorimetry (DSC) and dynamic mechanical analysis (DMA). Although DSC and DMA can provide relatively accurate results, they require laboratory environments, are time-consuming, and require specialized technicians for data analysis. In modern factories that pursue efficient production, rapid quality inspection, and cost control, traditional testing methods are insufficient to meet production demands. Therefore, there is an urgent need for a precise glass transition temperature testing method that can be used on-site in industrial production. Summary of the Invention

[0006] This application provides a method, apparatus, device, computer storage medium, and computer program product for testing glass transition temperature, which can achieve rapid and accurate determination of glass transition temperature.

[0007] In a first aspect, embodiments of this application provide a method for testing glass transition temperature, including:

[0008] Near-infrared spectroscopy is performed on the test object in the target environment to obtain the near-infrared spectral signal of the test object. The test object includes the test material and / or product, and the test object contains the target polymer.

[0009] The near-infrared spectral signal of the object to be tested is input into a pre-trained glass transition temperature (GLT) determination model. This model is trained using a training sample set, which includes multiple training samples. These training samples consist of multiple near-infrared spectral signals obtained by performing near-infrared spectral tests on multiple standard samples under multiple preset conditions and in a target environment, along with multiple GLT labels corresponding to each near-infrared spectral signal. The preset conditions include test conditions designed based on uncontrollable parameters corresponding to the target environment, including environmental parameters. The standard samples contain the target polymer and include multiple standard samples with different uncontrollable product parameters, including at least one of color, raw material ratio of the target polymer, moisture content, composite material parameters of the target polymer, and composite material structural parameters. The GLT label represents the calibrated GLT of the target polymer in the standard sample corresponding to the near-infrared spectral signal.

[0010] By using a trained glass transition temperature model, and based on the correspondence between near-infrared spectral signals and glass transition temperatures, the glass transition temperature corresponding to the near-infrared spectral signal of the test object is determined.

[0011] In one alternative implementation, before inputting the near-infrared spectral signal of the object to be tested into a pre-trained glass transition temperature determination model, the method further includes:

[0012] Near-infrared spectroscopy tests were performed on multiple standard samples under multiple preset conditions and in the target environment to obtain the near-infrared spectral signal of each standard sample under each preset condition.

[0013] Obtain the calibration glass transition temperature of the target polymer in each standard sample;

[0014] Training samples are created by taking the near-infrared spectral signal of each standard sample under each preset condition and the calibration glass transition temperature of the standard sample, thus obtaining a training sample set.

[0015] Input the training sample set into the glass transition temperature determination model;

[0016] Using a glass transition temperature measurement model, the glass transition temperature of each training sample is obtained according to the pre-defined correspondence between near-infrared spectral signals and glass transition temperatures.

[0017] Based on the measured glass transition temperature and calibration glass transition temperature corresponding to each training sample, the glass transition temperature measurement model is iteratively trained to adjust the correspondence between the near-infrared spectral signal and the glass transition temperature, thus obtaining a well-trained glass transition temperature measurement model.

[0018] In one optional implementation, before performing near-infrared spectroscopy tests on multiple standard samples under multiple preset conditions and in a target environment, the method further includes:

[0019] Obtain the boundary values ​​of uncontrollable parameters corresponding to the target environment;

[0020] Determine the range of uncontrollable parameters based on their boundary values;

[0021] Based on the value range of the uncontrollable parameter, multiple preset conditions are designed. These preset conditions include test conditions corresponding to the boundary values ​​of the uncontrollable parameter and test conditions corresponding to at least one intermediate value of the uncontrollable parameter.

[0022] In one optional implementation, before performing near-infrared spectroscopy tests on multiple standard samples under multiple preset conditions and in a target environment, the method further includes:

[0023] Obtain the boundary values ​​of uncontrollable product parameters corresponding to standard samples in the target production line;

[0024] Determine the value range of uncontrollable product parameters based on their boundary values;

[0025] Based on the value range of the uncontrollable product parameters, multiple standard samples are prepared. These standard samples include standard samples corresponding to the boundary values ​​of the uncontrollable product parameters and standard samples corresponding to the intermediate values ​​of at least one uncontrollable product parameter.

[0026] In one optional implementation, obtaining the calibrated glass transition temperature of the target polymer in each standard sample includes:

[0027] The target glass transition temperature is determined by testing each standard sample using a method for measuring the target glass transition temperature, which includes differential scanning calorimetry and / or dynamic mechanical analysis.

[0028] In one alternative implementation, the wavelength for near-infrared spectroscopy testing is 780 nm to 2526 nm.

[0029] In one alternative embodiment, the target polymer includes thermosetting polymers and / or thermoplastic polymers.

[0030] Secondly, embodiments of this application provide a glass transition temperature testing device, comprising:

[0031] The test module is used to perform near-infrared spectroscopy tests on the test object in the target environment to obtain the near-infrared spectral signal of the test object. The test object includes the test material and / or product, and the test object contains the target polymer.

[0032] The input module is used to input the near-infrared spectral signal of the object to be tested into a pre-trained glass transition temperature (GLT) determination model. The GLT determination model is trained using a training sample set. The training sample set includes multiple training samples, each containing near-infrared spectral signals obtained by performing near-infrared spectral tests on multiple standard samples under multiple preset conditions and in a target environment, and multiple GLT labels corresponding to these near-infrared spectral signals. The preset conditions include test conditions designed based on uncontrollable parameters corresponding to the target environment, including environmental parameters. The standard samples include the target polymer and multiple standard samples with different uncontrollable product parameters, including at least one of color, raw material ratio of the target polymer, moisture content, composite material parameters of the target polymer, and composite material structural parameters. The GLT label represents the calibrated GLT of the target polymer in the standard sample corresponding to the near-infrared spectral signal.

[0033] The determination module is used to determine the glass transition temperature corresponding to the near-infrared spectral signal of the object under test by using a trained glass transition temperature model and according to the correspondence between near-infrared spectral signal and glass transition temperature.

[0034] Thirdly, embodiments of this application provide a glass transition temperature testing device, the device comprising:

[0035] A processor and a memory storing computer program instructions; a method for testing the glass transition temperature that enables any of the above-mentioned features when the processor executes the computer program instructions.

[0036] Fourthly, embodiments of this application provide a computer storage medium storing computer program instructions, which, when executed by a processor, implement the glass transition temperature testing method described above.

[0037] Fifthly, embodiments of this application provide a computer program product in which instructions, when executed by a processor of an electronic device, enable the electronic device to perform any of the glass transition temperature testing methods described above.

[0038] The glass transition temperature (GLT) testing method, apparatus, device, computer storage medium, and computer program product of this application embodiment can perform near-infrared spectral testing on a test object in a target environment to obtain the GLT spectral signal of the test object. The test object includes a test material and / or product, and may contain a target polymer. Then, the GLT spectral signal of the test object is input into a pre-trained glass transition temperature (GLT) measurement model. The GLT measurement model is trained using a training sample set. This training sample set includes multiple training samples. These multiple training samples include multiple near-infrared spectral signals obtained by performing near-infrared spectral testing on multiple standard samples under multiple preset conditions in a target environment, and multiple GLT labels corresponding one-to-one with the multiple near-infrared spectral signals. The near-infrared spectral signals of the training sample set are all measured in the target environment. Thus, for a relatively fixed and controllable production environment, a corresponding target environment can be designed, making the GLT measurement model applicable to a specific production environment. The multiple preset conditions include test conditions designed based on uncontrollable parameters corresponding to the target environment, including environmental parameters. Multiple standard samples contain the target polymer and include multiple standard samples with different uncontrollable product parameters. These uncontrollable product parameters include at least one of the following: color, raw material ratio of the target polymer, moisture content, composite material parameters of the target polymer, and composite material structural parameters. The glass transition temperature (GTH) label is the calibrated GTH of the target polymer in the standard sample corresponding to the near-infrared spectral signal. Thus, the training sample set contains more comprehensive training samples, covering as many possible results in the industrial environment, facing various uncontrollable testing environmental and product factors, in the context of GTH testing. The calibrated GTH of the target polymer in the standard samples is then used as the GTH label for the training samples. In this way, the trained GTH measurement model can accurately determine the GTH of the target polymer in the test object based on the near-infrared spectral signals collected at the production site. This allows the use of a portable near-infrared spectrometer as a measurement tool for non-destructive testing in industrial production sites, making GTH testing both convenient and accurate. This application utilizes a trained glass transition temperature model to determine the glass transition temperature corresponding to the near-infrared spectral signal of the object under test, based on the correspondence between near-infrared spectral signals and glass transition temperatures. This enables rapid and accurate measurement of the glass transition temperature in diverse industrial applications, thereby improving production efficiency and product quality management capabilities. Attached Figure Description

[0039] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 is a schematic flowchart of a glass transition temperature testing method provided in an embodiment of this application;

[0041] Figure 2 is a flowchart illustrating a glass transition temperature testing method provided in another embodiment of this application;

[0042] Figure 3 is a schematic diagram of the glass transition temperature testing device provided in another embodiment of this application;

[0043] Figure 4 is a schematic diagram of the glass transition temperature testing device provided in another embodiment of this application. Detailed Implementation

[0044] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0045] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0046] Currently, the commonly used methods for measuring glass transition temperature in industrial production are differential scanning calorimetry (DSC) and dynamic mechanical analysis (DMA). Although DSC and DMA can provide relatively accurate results, they require laboratory environments, are time-consuming to operate, and require specialized technicians for data analysis. In modern factories that pursue efficient production, rapid quality inspection, and cost control, traditional testing methods are difficult to meet production needs.

[0047] Near-infrared spectroscopy (NIR) technology is currently widely used as a highly efficient and non-destructive quality control tool in the food, chemical, and pharmaceutical industries. NIR light falls between the visible and mid-infrared regions, with a wavelength range of 780 nm to 2526 nm and a wavenumber range of 12500 cm⁻¹. -1 ~4000cm -1 Near-infrared spectroscopy belongs to molecular vibrational spectroscopy, originating from the non-harmonic vibrations of covalent chemical bonds. It consists of overtones and combination frequencies of molecular vibrations. The near-infrared spectral signals of polymers cover the vibrational overtones and combination frequencies of various molecular groups such as CH, OH, and NH. Subtle changes in these frequency bands directly reflect microscopic changes in the internal structure and physical state of the polymer. When the composition of a sample changes, its near-infrared spectral signal will also change accordingly.

[0048] The related technology involves exploring the feasibility of measuring the glass transition temperature of epoxy resins using NIR (near-infrared) light. Specifically, it involves using near-infrared light with a wavelength range of 830 nm to 2630 nm to measure the glass transition temperature of epoxy resins with a glass transition temperature range of 45°C to 98°C. However, this approach has low accuracy and is insufficient to meet industrial-grade requirements.

[0049] Related technologies also involve near-infrared spectroscopy analysis using near-infrared light with wavelengths ranging from 2000 nm to 2450 nm to measure the glass transition temperature of epoxy prepregs, which range from 25°C to 42°C. However, this approach has limited applicability, being applicable only to epoxy resin prepregs, and the temperature range is narrow.

[0050] Furthermore, both solutions share common limitations: firstly, both only consider laboratory conditions, and in the complex real-world application scenarios of factories, neither can meet the accuracy requirements for industrial applications. Secondly, both solutions use near-infrared spectrometers designed for laboratory environments, and the entire set of equipment is heavy and not conducive to use in industrial production sites.

[0051] In summary, although preliminary research has been conducted in the laboratory on the use of NIR technology to measure glass transition temperature, it is not yet applicable to industrial applications. The accuracy, applicability, and convenience of NIR technology in industrial applications all need improvement.

[0052] To solve the above problems, the inventors, after in-depth thinking, ingeniously proposed a glass transition temperature testing method, device, equipment, computer storage medium, and computer program product.

[0053] The glass transition temperature testing method provided in this application will be described below with reference to the accompanying drawings and specific embodiments and application scenarios. The glass transition temperature testing method provided in this application can be executed by a glass transition temperature testing device, or a portion of the glass transition temperature testing device used to execute the glass transition temperature testing method. This application uses the execution of the glass transition temperature testing method by a glass transition temperature testing device as an example to describe in detail the glass transition temperature testing method provided in this application.

[0054] Furthermore, it should be noted that the glass transition temperature testing method provided in this application requires, after obtaining the near-infrared spectral signal of the test object by performing near-infrared spectral testing on the test object in the target environment, to determine the glass transition temperature corresponding to the near-infrared spectral signal using a glass transition temperature measurement model. Therefore, before determining the glass transition temperature corresponding to the near-infrared spectral signal using the glass transition temperature measurement model, the glass transition temperature measurement model needs to be trained first. The specific implementation method of the training method for the glass transition temperature measurement model used in the glass transition temperature testing method provided in this application is described below.

[0055] Figure 1 shows a flowchart of a glass transition temperature testing method provided in one embodiment of this application. Specifically, it can be a flowchart of the training method for the glass transition temperature measurement model used in the glass transition temperature testing method provided in this embodiment of the application.

[0056] As shown in Figure 1, the training method for the glass transition temperature measurement module used in the glass transition temperature test method provided in this application embodiment may include steps S110 to S160.

[0057] S110, Near-infrared spectroscopy tests are performed on multiple standard samples under multiple preset conditions and in a target environment to obtain the near-infrared spectral signal of each standard sample under each preset condition; wherein, the multiple preset conditions include test conditions designed according to uncontrollable parameters corresponding to the target environment, and the uncontrollable parameters include environmental parameters; the multiple standard samples contain a target polymer, and the multiple standard samples include multiple standard samples with different uncontrollable product parameters, and the uncontrollable product parameters include at least one of color, raw material ratio of the target polymer, moisture content, composite material parameters of the target polymer, and composite material structural parameters.

[0058] Step S110 can differentiate between controllable and uncontrollable parameters that affect the accuracy of glass transition temperature measurement in actual factory environments, fix the controllable parameters, and design comprehensive and representative measurement samples and test environments for the uncontrollable parameters. Specifically, in step S110, the target environment can be a fixed test environment designed based on the controllable parameters of the industrial production site. For example, the target environment can be a factory environment with the measurement background controlled as a fixed background. Multiple preset conditions can be multiple measurement environments designed based on the uncontrollable environmental parameters of the industrial production site. For example, the uncontrollable parameters corresponding to the target environment can include uncontrollable environmental parameters in the factory environment, such as, but not limited to, one or more of the following: ambient temperature, relative humidity, and environmental pollutants that may exist in the factory environment. Multiple standard samples can be measurement samples with a fixed product structure but different uncontrollable product parameters, designed based on the controllable structural parameters and uncontrollable product parameters of the material and / or product. For example, they can be specially made measurement samples based on the surface structure of the product. Among the uncontrollable product parameters, the composite material parameters of the target polymer can include, for example, the types of other materials compounded with the target polymer in the composite material, including but not limited to the types of fabrics and core materials; the structural parameters of the composite material can include but not limited to the relative orientation between fabrics and the surface morphology of the core material. It is understood that the above-mentioned controllable and uncontrollable parameters are not fixed and can be adjusted according to actual needs. For example, some industrial production environments have strict requirements on ambient temperature and relative humidity, so ambient temperature and relative humidity can also be considered as controllable parameters.

[0059] It is understood that the aforementioned target environment may include a fixed test environment designed for the same industrial production site, and the aforementioned multiple standard samples may include measurement samples with different uncontrollable product parameters designed for the same material or product. When it is necessary to train a glass transition temperature measurement model applicable to multiple industrial production sites and / or multiple materials and / or products, controllable and uncontrollable parameters can be distinguished for each material and / or product in each industrial production site. The controllable parameters can be fixed, and for the uncontrollable parameters, comprehensive and representative measurement samples and test environments can be designed, and corresponding near-infrared spectral signals can be collected.

[0060] S120, obtain the calibration glass transition temperature of the target polymer in each standard sample.

[0061] In step S120, calibrating the glass transition temperature may include obtaining the glass transition temperature using a highly accurate glass transition temperature testing method. This calibrated glass transition temperature has high accuracy and can be considered as the actual glass transition temperature of the target polymer in the standard sample.

[0062] S130, create training samples by taking the near-infrared spectral signal of each standard sample under each preset condition and the corresponding calibration glass transition temperature of the standard sample, and obtain the training sample set.

[0063] In step S130, the calibrated glass transition temperature corresponding to the standard sample can be used as a glass transition temperature label to measure the effectiveness of model training.

[0064] S140, input the training sample set into the glass transition temperature determination model.

[0065] In step S140, the glass transition temperature determination model may include a correction prediction model constructed using mathematical algorithms, such as partial least squares regression, principal component regression, multiple linear regression, or neural network algorithms. This application does not impose any particular limitation on this aspect.

[0066] S150 uses a glass transition temperature measurement model to obtain the glass transition temperature of each training sample according to a preset correspondence between near-infrared spectral signals and glass transition temperatures.

[0067] S160, based on the measured glass transition temperature and the calibrated glass transition temperature corresponding to each training sample, the glass transition temperature measurement model is iteratively trained to adjust the correspondence between the near-infrared spectral signal and the glass transition temperature, thus obtaining the trained glass transition temperature measurement model.

[0068] In step S160, the glass transition temperature (GLT) measurement model can be iteratively trained based on the measured and calibrated GLTs corresponding to each training sample until a preset training stopping condition is met, resulting in a trained GLT measurement model. This training stopping condition can be, for example, reaching a preset number of iterations, or the performance of the GLT measurement model meeting preset requirements; it is not limited here. For example, the measured and calibrated GLTs of each training sample can be calculated to determine the deviation function value of the GLT measurement model. If the deviation function value is less than a preset threshold, the trained GLT measurement model is obtained.

[0069] According to the above embodiments, near-infrared spectroscopy tests can be performed on multiple standard samples under multiple preset conditions and in a target environment to obtain the near-infrared spectral signal of each standard sample under each preset condition. The multiple preset conditions include test conditions designed based on uncontrollable parameters corresponding to the target environment, including environmental parameters. The multiple standard samples contain a target polymer and include multiple standard samples with different uncontrollable product parameters, including at least one of color, raw material ratio of the target polymer, moisture content, composite material parameters of the target polymer, and composite material structural parameters. In this way, a corresponding target environment can be designed for a relatively fixed and controllable production site environment; multiple standard samples with different uncontrollable product parameters can be designed for uncontrollable product parameters; and multiple preset conditions can be designed for uncontrollable test environment factors. Thus, the near-infrared spectral signals of each standard sample under each preset condition are relatively comprehensive, and can cover as many possible results as possible in the glass transition temperature test site in an industrial environment.

[0070] Subsequently, the calibrated glass transition temperature (GTH) of the target polymer in each standard sample can be obtained. This calibrated GTH has high accuracy and can be considered as the actual GTH of the target polymer in the standard sample. Next, training samples are created by comparing the near-infrared spectral signal of each standard sample under each preset condition with the corresponding calibrated GTH, resulting in a training sample set. This training sample set contains a rich variety of samples and is highly representative. The training sample set is then input into the glass transition temperature (GTH) measurement model. Using the GTH measurement model, according to the preset correspondence between near-infrared spectral signals and GTH, the measured GTH of each training sample is obtained. Based on the measured GTH and calibrated GTH of each training sample, the GTH measurement model is iteratively trained to adjust the correspondence between near-infrared spectral signals and GTH, resulting in a trained GTH measurement model. This trained model is then used to determine the GTH of the target polymer in the test object. In this way, the trained glass transition temperature determination model can accurately determine the glass transition temperature of the corresponding target polymer based on the near-infrared spectral signals collected at the production site.

[0071] The glass transition temperature (GLT) measurement model trained according to the above embodiments can achieve high accuracy in industrial production environments. This allows the use of portable near-infrared spectrometers (e.g., handheld near-infrared spectrometers) as measurement tools for non-destructive, rapid, and accurate measurement of the GLT of raw materials and products in industrial applications. Therefore, the GLT testing method based on this model has high applicability and can be applied to the production and maintenance of components and products in aerospace, wind power, energy storage, marine, and automotive fields. Applicable raw materials can include thermosetting and thermoplastic polymers, as well as composite materials based on these materials. Applicable products include, but are not limited to, composite material components used in aircraft, wind turbine blades, energy storage tanks, automotive parts, coatings, adhesives, and structural adhesives.

[0072] In one embodiment, before performing near-infrared spectroscopy tests on multiple standard samples under multiple preset conditions and in a target environment, the method may further include:

[0073] Obtain the boundary values ​​of uncontrollable parameters corresponding to the target environment.

[0074] Determine the range of uncontrollable parameters based on their boundary values.

[0075] Based on the value range of the uncontrollable parameter, multiple preset conditions are designed. These preset conditions include test conditions corresponding to the boundary values ​​of the uncontrollable parameter and test conditions corresponding to at least one intermediate value of the uncontrollable parameter.

[0076] In the above embodiments, the boundary value may include the extreme value that the uncontrollable parameter can reach under the target environment, or the extreme value that it may reach. The value range of the uncontrollable parameter can represent the selectable range of the uncontrollable parameter. Based on the value range of the uncontrollable parameter, multiple preset conditions are designed, which may include test conditions corresponding to the boundary values ​​of the uncontrollable parameter and test conditions corresponding to at least one intermediate value of the uncontrollable parameter. In some examples, the uncontrollable parameter may include multiple environmental parameters, and multiple environmental parameters can be combined based on the value range of each environmental parameter so that the designed multiple preset conditions can cover as many changes as possible in the actual production environment.

[0077] According to the above implementation method, by obtaining the boundary values ​​of uncontrollable parameters corresponding to the target environment, the value range of the uncontrollable parameters is determined, and then multiple preset conditions are designed based on the value range of the uncontrollable parameters. This allows the multiple preset conditions to cover as many variations as possible in the actual production environment, thereby improving the comprehensiveness and representativeness of the training samples. Thus, the glass transition temperature measurement model can maintain high accuracy even when facing variable uncontrollable environmental parameters in the target environment, thereby improving the accuracy and flexibility of glass transition temperature testing.

[0078] In one embodiment, before performing near-infrared spectroscopy tests on multiple standard samples under multiple preset conditions and in a target environment, the method may further include:

[0079] Obtain the boundary values ​​of uncontrollable product parameters corresponding to the standard sample in the target production line.

[0080] Determine the value range of uncontrollable product parameters based on their boundary values.

[0081] Based on the value range of the uncontrollable product parameters, multiple standard samples are prepared. These standard samples include standard samples corresponding to the boundary values ​​of the uncontrollable product parameters and standard samples corresponding to the intermediate values ​​of at least one uncontrollable product parameter.

[0082] In the above embodiments, boundary values ​​may include the extreme values, or potential extreme values, that the uncontrollable product parameters corresponding to the standard samples in the target production line can reach. The value range of the uncontrollable product parameters can represent the selectable range of the uncontrollable parameters. Based on the value range of the uncontrollable product parameters, multiple standard samples are prepared, which may include preparing standard samples corresponding to the boundary values ​​of the uncontrollable product parameters and standard samples corresponding to the intermediate values ​​of at least one uncontrollable product parameter. For example, taking the color of the target polymer as an example, for the natural color differences between different batches, a sample set containing color gradients needs to be designed, from the lightest to the darkest, and its span needs to exceed the color range used in actual production. In this way, the influence of these uncontrollable variables can be effectively corrected for the small differences between raw material or product batches by means of chemical quantitative analysis. In some examples, there can be multiple uncontrollable product parameters, and multiple uncontrollable product parameters can be combined based on the value range of each uncontrollable product parameter so that the prepared multiple standard samples can cover as many changes as possible in the actual production environment.

[0083] According to the above implementation method, by obtaining the boundary values ​​of uncontrollable product parameters corresponding to the target environment, the value range of the uncontrollable product parameters is determined, and then multiple standard samples are prepared based on the value range of the uncontrollable product parameters. This allows the multiple standard samples to cover as many variations as possible in the actual production environment, thereby improving the comprehensiveness and representativeness of the training samples. Thus, the glass transition temperature measurement model can maintain high accuracy when facing the variable uncontrollable product parameters in industrial production, thereby improving the accuracy and flexibility of glass transition temperature testing.

[0084] In one embodiment, obtaining the calibrated glass transition temperature of the target polymer in each standard sample may specifically include:

[0085] The target glass transition temperature is determined by testing each standard sample using a method for measuring the target glass transition temperature, which includes differential scanning calorimetry and / or dynamic mechanical analysis.

[0086] According to the above embodiments, the calibrated glass transition temperature of the target polymer in each standard sample is determined by differential scanning calorimetry and / or dynamic mechanical analysis. Both differential scanning calorimetry and dynamic mechanical analysis have high accuracy, and the calibrated glass transition temperatures determined by these two methods are close to the actual glass transition temperatures of the target polymer in the standard samples. Therefore, using the calibrated glass transition temperature as a label for training samples can improve the accuracy of the glass transition temperature determination model.

[0087] In one embodiment, near-infrared spectroscopy tests are performed on multiple standard samples under multiple preset conditions and in a target environment to obtain the near-infrared spectral signal of each standard sample under each preset condition. Specifically, this may include:

[0088] Near-infrared spectroscopy tests were performed on multiple standard samples under multiple preset conditions and in the target environment to obtain the original near-infrared spectral signal of each standard sample under each preset condition.

[0089] The original near-infrared spectral signals of each standard sample under various preset conditions are preprocessed to obtain the near-infrared spectral signals of each standard sample under various preset conditions.

[0090] The above preprocessing can be implemented using preprocessing methods known in the art, such as, but not limited to, applying smoothing techniques to remove random noise, performing normalization operations to standardize the data distribution, and revealing at least one of the potential spectral features through first-order and second-order derivative transformations.

[0091] According to the above embodiments, preprocessing the raw near-infrared spectral signal helps to extract the spectral characteristics of the target polymer system exhibiting changes in glass transition temperature under production conditions. This allows the glass transition temperature measurement model to accurately identify the potential relationship between the glass transition temperature and the near-infrared spectral signal, thereby improving the accuracy of glass transition temperature testing.

[0092] This application does not limit the wavelength of near-infrared spectroscopy testing. In this application, the glass transition temperature (GLT) measurement model used in the glass transition temperature testing method has high accuracy and applicability, and a wide range of applications. Therefore, depending on the chemical structure of the target polymer, the wavelength of near-infrared spectroscopy testing can be any part of the wavelength range between 780 nm and 2526 nm. For example, it can be 780 nm–2526 nm, 780 nm–2400 nm, 780 nm–2200 nm, 780 nm–2000 nm, 780 nm–1800 nm, 780 nm–1600 nm, 780 nm–1200 nm, 780 nm–1000 nm, 800 nm–2526 nm, 800 nm–2300 nm, 800 nm–2100 nm, 800 nm–1900 nm, 800 nm–1500 nm, etc.

[0093] In this way, different test wavelengths can be selected for different target polymers, thus ensuring high accuracy in the determination of the glass transition temperature of different target polymers.

[0094] In one embodiment, after iteratively training the glass transition temperature measurement model based on the measured glass transition temperature and the calibrated glass transition temperature corresponding to each training sample, the method may further include:

[0095] The performance of the glass transition temperature determination model is verified using actual industrial materials and / or actual products corresponding to standard samples, in order to adjust the model parameters of the glass transition temperature determination model.

[0096] In this way, the glass transition temperature determination model can be optimized and calibrated using actual industrial materials and / or actual products, thereby further improving the accuracy of the model.

[0097] In one embodiment, the wavelength for near-infrared spectroscopy testing can be 950 nm to 1650 nm. This allows for a balance between high accuracy, wide applicability, and low instrument manufacturing costs.

[0098] In one embodiment, the target polymer may include thermosetting polymers and / or thermoplastic polymers.

[0099] For example, the aforementioned thermosetting polymeric materials may include epoxy resins, unsaturated polyesters, polyurethanes, and their modified, block, hybrid, or blended materials and systems. For example, the aforementioned thermoplastic polymeric materials may include free-radical polymerized polyolefins, and their modified, block, hybrid, or blended polyolefin materials and systems.

[0100] The glass transition temperature testing method provided in the embodiments of this application will be described in detail below with reference to Figure 2.

[0101] Figure 2 shows a schematic flowchart of a glass transition temperature testing method according to an embodiment of this application. As shown in Figure 2, the glass transition temperature testing method may specifically include the following steps S210 to S230.

[0102] S210, Near-infrared spectroscopy test is performed on the test object in the target environment to obtain the near-infrared spectral signal of the test object. The test object includes the test material and / or product, and the test object contains the target polymer.

[0103] In step S210, the object to be tested may include the surface structure of the product or its raw materials.

[0104] S220, the near-infrared spectral signal of the object to be tested is input into a pre-trained glass transition temperature (GLT) determination model, which is trained using a training sample set. The training sample set includes multiple training samples. These training samples include multiple near-infrared spectral signals obtained by performing near-infrared spectral tests on multiple standard samples under multiple preset conditions and in a target environment, and multiple GLT labels corresponding one-to-one with each near-infrared spectral signal. The multiple preset conditions include test conditions designed based on uncontrollable parameters corresponding to the target environment, including environmental parameters. The multiple standard samples contain the target polymer and include multiple standard samples with different uncontrollable product parameters, including at least one of color, raw material ratio of the target polymer, moisture content, composite material parameters of the target polymer, and composite material structural parameters. The GLT label is the calibrated GLT of the target polymer in the standard sample corresponding to the near-infrared spectral signal.

[0105] S230 uses a trained glass transition temperature model to determine the glass transition temperature corresponding to the near-infrared spectral signal of the test object according to the correspondence between the near-infrared spectral signal and the glass transition temperature.

[0106] The glass transition temperature (GLT) testing method of this application embodiment can perform near-infrared spectroscopy testing on the test object in a target environment to obtain the GLT spectral signal of the test object. The test object includes the test material and / or product, and the test object contains a target polymer. Then, the GLT spectral signal of the test object is input into a pre-trained glass transition temperature (GLT) measurement model. The GLT measurement model is trained using a training sample set. This training sample set includes multiple training samples. These multiple training samples include multiple near-infrared spectral signals obtained by performing near-infrared spectroscopy testing on multiple standard samples under multiple preset conditions in the target environment, and multiple GLT labels corresponding one-to-one with the multiple near-infrared spectral signals. The near-infrared spectral signals of the above training sample set are all measured in the target environment. Thus, for a relatively fixed and controllable production environment, a corresponding target environment can be designed, making the GLT measurement model applicable to a specific production environment. The multiple preset conditions include test conditions designed based on uncontrollable parameters corresponding to the target environment, including environmental parameters. Multiple standard samples contain the target polymer and include multiple standard samples with different uncontrollable product parameters. These uncontrollable product parameters include at least one of the following: color, raw material ratio of the target polymer, moisture content, composite material parameters of the target polymer, and composite material structural parameters. The glass transition temperature (GTH) label is the calibrated GTH of the target polymer in the standard sample corresponding to the near-infrared spectral signal. Thus, the training sample set contains more comprehensive training samples, covering as many possible results in the industrial environment, facing various uncontrollable testing environmental and product factors, in the context of GTH testing. The calibrated GTH of the target polymer in the standard samples is then used as the GTH label for the training samples. In this way, the trained GTH measurement model can accurately determine the GTH of the target polymer in the test object based on the near-infrared spectral signals collected at the production site. This allows the use of a portable near-infrared spectrometer as a measurement tool for non-destructive testing in industrial production sites, making GTH testing both convenient and accurate. This application utilizes a trained glass transition temperature model to determine the glass transition temperature corresponding to the near-infrared spectral signal of the object under test, based on the correspondence between near-infrared spectral signals and glass transition temperatures. This enables rapid and accurate measurement of the glass transition temperature in diverse industrial applications, thereby improving production efficiency and product quality management capabilities.

[0107] To better describe the overall solution, based on the above embodiments, a specific example is given to illustrate the glass transition temperature testing method of this application. This will be explained in detail below. It should be noted that the following example is only for explaining the embodiments of this application and does not constitute a limitation on the embodiments of this application.

[0108] As an example, the glass transition temperature test method may include the following steps S310 to S360.

[0109] S310 identifies parameters that affect the accuracy of glass transition temperature testing in a factory environment.

[0110] In step S310, parameters affecting the accuracy of the glass transition temperature test can include parameters affecting near-infrared spectral signal acquisition, particularly factors affecting the absorption characteristics and signal intensity feedback of the near-infrared spectrum. For example, these can include environmental parameters, polymer-related parameters, polymer composite material parameters, and composite material structural parameters. Polymer composite material parameters can include the types of materials within the depth range that near-infrared light can penetrate during measurement, while composite material structural parameters can include the layup sequence and interface structure of the composite material. For example, environmental factors can include ambient temperature, relative humidity, and environmental pollutants. Polymer-related parameters can include color, polymer raw material ratio (e.g., the mixing ratio of resin and curing agent), and moisture content. The polymer composite material parameters and composite material structural parameters can be determined by the actual conditions of the product. For example, polymer composite material parameters can include, in addition to the polymer matrix material, the types of composite materials within the depth range that near-infrared light can penetrate, such as reinforcing materials combined with the polymer matrix material, including but not limited to glass fiber, carbon fiber, aramid fiber, boron fiber, silicon carbide fiber, and natural fibers. For the same type of fiber, different types of fabrics can be distinguished, such as ordinary modulus uniaxial fabrics, ordinary modulus biaxial fabrics, ordinary modulus triaxial fabrics, high modulus uniaxial fabrics, high modulus biaxial fabrics, high modulus triaxial fabrics, ultra-high modulus uniaxial fabrics, ultra-high modulus biaxial fabrics, and ultra-high modulus triaxial fabrics. For example, materials within the near-infrared light penetration depth range can also include foams used for weight reduction and stiffness increase, such as poly(ethylene terephthalate) (PET), polyvinyl chloride (PVC), polyurethane (PU), polystyrene (PS), polymethacrylamide (PMI), acrylonitrile-styrene foam, polyethylene foam, balsa wood, engineered foam, etc. Composite material structural parameters can include various combinations of composite material layups, the number of fabric layers used, and the angles between fabrics. Composite material structural parameters can also include the surface properties of the composite material, such as the surface structure of foam and balsa wood (including but not limited to grooved structures, the structure and distribution of engineered foam reinforcement materials, etc.).

[0111] S320 uses fixed controllable parameters and designs training sample sets for uncontrollable parameters.

[0112] In step S320, fixing the controllable parameters may include fixing the test environment and fixing the test object. For example, fixing the test environment may include a specific factory environment, and the background for controlling the measurement is a fixed background. Fixing the test object may include a specific type of product or raw material, and fixing the specifications of the test object. Fixing the controllable parameters may specifically refer to simplifying the influencing factor system, where the production process allows. For example, in the case of reinforced composite materials, the outer surface material contacted by the near-infrared spectrometer can be used as a design prototype to create a sample that can be peeled off from the product or component without causing damage. When the outer surface of the product is made of reinforced composite material, the sample thickness can be adjusted according to the number of fabric layers, whether single-layer, double-layer, or multi-layer, depending on the influence of fabric thickness on the accuracy of glass transition temperature measurement, and the balance between accuracy and ease of operation. When the sample is a multi-layer fabric structure, the fabric fibers can be designed to have the same orientation or maintain a certain angle. Without affecting the accuracy of glass transition temperature measurement, it is not necessary to strictly control the relative orientation between the fibers of each layer of fabric. After the production process of a product or component is completed, these samples can be safely removed from the production line, and their glass transition temperature can be measured using near-infrared spectroscopy without affecting the spectral quality.

[0113] Designing a training sample set for uncontrollable parameters involves designing and constructing a comprehensive training sample set to ensure it fully represents various scenarios in the actual production environment. When designing the training sample set, in addition to covering all variations under normal production conditions, the scope needs to be expanded to ensure that the training samples maintain their representativeness and effectiveness even under extreme or boundary conditions. Taking polymer color as an example, to address the natural color differences between different batches, a sample set containing color gradients needs to be designed, from the lightest to the darkest, with a range exceeding the color range used in actual production. In this way, the minor differences between raw material batches can be effectively corrected for the impact of these uncontrollable variables using quantitative chemical analysis. For example, designing a training sample set for uncontrollable parameters may include designing multiple test conditions corresponding to different environmental parameters for uncontrollable environmental parameters, and designing multiple standard samples with different uncontrollable product parameters for uncontrollable product parameters. The implementation method for constructing the training sample set has been described in detail above and will not be repeated here.

[0114] S330 collects near-infrared spectral signals of training samples and calibrates glass transition temperatures.

[0115] In step S330, near-infrared spectral signals of training samples in the training sample set are acquired. This may include acquiring the corresponding raw near-infrared spectral signals of each training sample in the training sample set under designed test conditions, and preprocessing the raw spectral signals, including but not limited to applying smoothing techniques to remove random noise, performing normalization operations to standardize the data distribution, and revealing potential spectral features through first-order and second-order derivative transformations. The glass transition temperature is then acquired and calibrated, which may include determining the glass transition temperature of each sample using differential scanning calorimetry or dynamic mechanical analysis, to serve as a glass transition temperature label for each training sample.

[0116] S340 uses a training sample set to train a glass transition temperature determination model.

[0117] S350 is validated using actual industrial raw materials and / or actual products from the factory to optimize the glass transition temperature determination model.

[0118] S360 acquires the near-infrared spectral signal of the test object, inputs it into the glass transition temperature determination model, and obtains the glass transition temperature of the target polymer in the test object.

[0119] The above example systematically identifies and controls parameters affecting the accuracy of glass transition temperature (GTH) measurements, distinguishes between controllable and uncontrollable parameters, and designs and constructs a training sample set. This improves the accuracy of GTH measurement using near-infrared spectroscopy in industrial applications, solving the problem of large measurement deviations caused by differences in environment, materials, and product structure in actual production applications of near-infrared spectroscopy, thus ensuring the reliability of measurement data. This GTH testing method is not only applicable to various thermosetting and thermoplastic polymers and their composites, but can also be widely used in quality testing of products in multiple industrial fields, including aerospace, wind power, energy storage, marine, automotive, and sporting goods, exhibiting high flexibility and universal applicability. The GTH testing method of this application effectively solves the limitations of laboratory-based near-infrared spectroscopy for measuring GTH in industrial applications, such as low measurement accuracy, narrow applicability, and inconvenience of on-site instrument operation. It provides a fast, accurate, and non-destructive technology for measuring the GTH of materials and products in related industrial sectors.

[0120] For the measurement of the glass transition temperature (GTH) of the shell and web of wind turbine blades, this application develops a near-infrared spectroscopy measurement technique based on the GTH testing method of the infused epoxy resin system A. This technique is used to non-destructively measure the GTH of glass fiber reinforced composite materials during the curing process. A GTH testing model was established using the method of this application, and this model was used to test the GTH of the shell and web. Statistical analysis was performed on the deviations between the more than two thousand GTH data output by the model and the GTH data measured by differential scanning calorimetry (DSC). The standard deviation between the GTH measured by near-infrared spectroscopy and the GTH measured by DSC was 3.0517℃. A measurement system analysis (MSA) was performed on the method for measuring the GTH using near-infrared spectroscopy on epoxy resin A. The analysis results are shown in Table 1. Table 1 shows that the coefficient of variation (SV) of this method is 1.67%, which meets the requirements of the quality control system.

[0121] Table 1

[0122] Based on the same inventive concept, this application also provides a glass transition temperature testing device.

[0123] As shown in Figure 3, the glass transition temperature testing device 300 may include a first testing module 301, a first input module 302, and a first determining module 303.

[0124] The first test module 301 is used to perform near-infrared spectroscopy testing on the test object in the target environment to obtain the near-infrared spectral signal of the test object. The test object includes the test material and / or product, and the test object contains the target polymer.

[0125] The first input module 302 is used to input the near-infrared spectral signal of the object to be tested into a pre-trained glass transition temperature (GLT) determination model. The GLT determination model is trained using a training sample set. The training sample set includes multiple training samples. Each training sample includes multiple near-infrared spectral signals obtained by performing near-infrared spectral tests on multiple standard samples under multiple preset conditions and in a target environment, and multiple GLT labels corresponding to each near-infrared spectral signal. The multiple preset conditions include test conditions designed based on uncontrollable parameters corresponding to the target environment, including environmental parameters. The multiple standard samples contain the target polymer and include multiple standard samples with different uncontrollable product parameters, including at least one of color, raw material ratio of the target polymer, moisture content, composite material parameters of the target polymer, and composite material structural parameters. The GLT label is the calibrated GLT of the target polymer in the standard sample corresponding to the near-infrared spectral signal.

[0126] The first determining module 303 is used to determine the measurement glass transition temperature corresponding to the near-infrared spectral signal of the object under test by using a trained glass transition temperature model and according to the correspondence between the near-infrared spectral signal and the glass transition temperature.

[0127] The glass transition temperature (GLT) testing device of this application embodiment can perform near-infrared spectral testing on the test object in a target environment to obtain the GLT spectral signal of the test object. The test object includes the test material and / or product, and the test object contains a target polymer. Then, the GLT spectral signal of the test object is input into a pre-trained glass transition temperature (GLT) measurement model. The GLT measurement model is trained using a training sample set. This training sample set includes multiple training samples. These multiple training samples include multiple near-infrared spectral signals obtained by performing near-infrared spectral testing on multiple standard samples under multiple preset conditions in the target environment, and multiple GLT labels corresponding one-to-one with the multiple near-infrared spectral signals. The near-infrared spectral signals of the training sample set are all measured in the target environment. Thus, for a relatively fixed and controllable production environment, a corresponding target environment can be designed, making the GLT measurement model applicable to a specific production environment. The multiple preset conditions include test conditions designed based on uncontrollable parameters corresponding to the target environment, including environmental parameters. Multiple standard samples contain the target polymer and include multiple standard samples with different uncontrollable product parameters. These uncontrollable product parameters include at least one of the following: color, raw material ratio of the target polymer, moisture content, composite material parameters of the target polymer, and composite material structural parameters. The glass transition temperature (GTH) label is the calibrated GTH of the target polymer in the standard sample corresponding to the near-infrared spectral signal. Thus, the training sample set contains more comprehensive training samples, covering as many possible results in the industrial environment, facing various uncontrollable testing environmental and product factors, in the context of GTH testing. The calibrated GTH of the target polymer in the standard samples is then used as the GTH label for the training samples. In this way, the trained GTH measurement model can accurately determine the GTH of the target polymer in the test object based on the near-infrared spectral signals collected at the production site. This allows the use of a portable near-infrared spectrometer as a measurement tool for non-destructive testing in industrial production sites, making GTH testing both convenient and accurate. This application utilizes a trained glass transition temperature model to determine the glass transition temperature corresponding to the near-infrared spectral signal of the object under test, based on the correspondence between near-infrared spectral signals and glass transition temperatures. This enables rapid and accurate measurement of the glass transition temperature in diverse industrial applications, thereby improving production efficiency and product quality management capabilities.

[0128] In one embodiment, the apparatus may further include:

[0129] The second testing module is used to perform near-infrared spectral tests on multiple standard samples under multiple preset conditions and in the target environment before inputting the near-infrared spectral signal of the object to be tested into the pre-trained glass transition temperature determination model, so as to obtain the near-infrared spectral signal of each standard sample under each preset condition.

[0130] The first acquisition module is used to acquire the calibration glass transition temperature of the target polymer in each standard sample.

[0131] A module is created to generate training samples by taking the near-infrared spectral signal of each standard sample under each preset condition and the corresponding calibration glass transition temperature of the standard sample, thus obtaining a training sample set.

[0132] The second input module is used to input the training sample set into the glass transition temperature determination model.

[0133] The processing module is used to obtain the glass transition temperature of each training sample by using a glass transition temperature measurement model and according to the preset correspondence between near-infrared spectral signals and glass transition temperatures.

[0134] The training module is used to iteratively train the glass transition temperature measurement model based on the measured glass transition temperature and the calibration glass transition temperature corresponding to each training sample, so as to adjust the correspondence between the near-infrared spectral signal and the glass transition temperature, and obtain the trained glass transition temperature measurement model.

[0135] In one embodiment, the apparatus may further include:

[0136] The second acquisition module is used to acquire the boundary values ​​of uncontrollable parameters corresponding to the target environment before performing near-infrared spectroscopy tests on multiple standard samples under multiple preset conditions and in the target environment.

[0137] The second determining module is used to determine the value range of the uncontrollable parameter based on its boundary values.

[0138] The design module is used to design multiple preset conditions based on the value range of the uncontrollable parameter. The multiple preset conditions include test conditions corresponding to the boundary values ​​of the uncontrollable parameter and test conditions corresponding to at least one intermediate value of the uncontrollable parameter.

[0139] In one embodiment, the apparatus may further include:

[0140] The third acquisition module is used to acquire the boundary values ​​of the uncontrollable product parameters corresponding to the standard samples in the target production line before conducting near-infrared spectroscopy tests on multiple standard samples under multiple preset conditions and in the target environment.

[0141] The third determining module is used to determine the value range of uncontrollable product parameters based on their boundary values.

[0142] The preparation module is used to prepare multiple standard samples based on the value range of uncontrollable product parameters. The multiple standard samples include standard samples corresponding to the boundary values ​​of the uncontrollable product parameters and standard samples corresponding to the intermediate values ​​of at least one uncontrollable product parameter.

[0143] In one embodiment, the first acquisition module is used to acquire the calibrated glass transition temperature of the target polymer in each standard sample, specifically including:

[0144] The testing submodule is used to test each standard sample using a target glass transition temperature determination method to obtain the calibrated glass transition temperature of the target polymer in each standard sample. The target glass transition temperature determination method includes differential scanning calorimetry and / or dynamic mechanical analysis.

[0145] In one embodiment, the wavelength for near-infrared spectroscopy testing can be from 780 nm to 2526 nm.

[0146] In one embodiment, the target polymer may include thermosetting polymers and / or thermoplastic polymers.

[0147] The glass transition temperature testing device provided in this application embodiment can realize the various processes implemented in the method embodiment of FIG2. To avoid repetition, it will not be described again here.

[0148] Figure 4 shows a schematic diagram of the hardware structure of the glass transition temperature testing device provided in an embodiment of this application.

[0149] The glass transition temperature testing device may include a processor 401 and a memory 402 storing computer program instructions.

[0150] Specifically, the processor 401 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0151] Memory 402 may include mass storage for data or instructions. For example, and not limitingly, memory 402 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 402 may include removable or non-removable (or fixed) media. Where appropriate, memory 402 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 402 is non-volatile solid-state memory.

[0152] Memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the methods according to one aspect of this disclosure.

[0153] The processor 401 reads and executes computer program instructions stored in the memory 402 to implement any of the glass transition temperature testing methods in the above embodiments.

[0154] As an example, the glass transition temperature testing device may also include a communication interface 404 and a bus 410. As shown in Figure 4, the processor 401, memory 402, and communication interface 404 are connected via the bus 410 and communicate with each other.

[0155] Communication interface 404 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0156] Bus 410 includes hardware, software, or both, that couples components of a glass transition temperature device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), an HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 410 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0157] The glass transition temperature testing device can perform the glass transition temperature testing method in the embodiments of this application, thereby realizing the glass transition temperature testing method and device described in conjunction with Figures 2 and 3.

[0158] Furthermore, in conjunction with the data processing methods in the above embodiments, this application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the data processing methods in the above embodiments.

[0159] This application also provides a computer program product, including a computer program, which, when executed, implements any of the glass transition temperature testing methods described in the above embodiments.

[0160] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0161] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0162] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0163] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0164] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for testing glass transition temperature, comprising: Near-infrared spectroscopy is performed on the test object in the target environment to obtain the near-infrared spectral signal of the test object, wherein the test object includes the test material and / or product, and the test object contains the target polymer; The near-infrared spectral signal of the object under test is input into a pre-trained glass transition temperature (GLT) determination model, wherein the GLT determination model is trained using a training sample set; the training sample set includes multiple training samples; the multiple training samples include multiple near-infrared spectral signals obtained by performing near-infrared spectral tests on multiple standard samples under multiple preset conditions in the target environment, and multiple GLT labels corresponding one-to-one with the multiple near-infrared spectral signals; the multiple preset conditions include test conditions designed based on uncontrollable parameters corresponding to the target environment, the uncontrollable parameters including environmental parameters; the multiple standard samples contain the target polymer, and the multiple standard samples include multiple standard samples with different uncontrollable product parameters, the uncontrollable product parameters including at least one of color, raw material ratio of the target polymer, moisture content, composite material parameters of the target polymer, and composite material structural parameters; the GLT label is the calibrated GLT of the target polymer in the standard sample corresponding to the near-infrared spectral signal. Using the trained glass transition temperature model, the glass transition temperature corresponding to the near-infrared spectral signal of the test object is determined according to the correspondence between the near-infrared spectral signal and the glass transition temperature.

2. The method according to claim 1, wherein, Before inputting the near-infrared spectral signal of the object to be tested into the pre-trained glass transition temperature determination model, the method further includes: Near-infrared spectroscopy tests were performed on the multiple standard samples under the multiple preset conditions and in the target environment to obtain the near-infrared spectral signal of each standard sample under each preset condition. Obtain the calibration glass transition temperature of the target polymer in each standard sample; Training samples are created by taking the near-infrared spectral signal of each standard sample under each preset condition and the calibration glass transition temperature of the standard sample, thus obtaining a training sample set. The training sample set is input into the glass transition temperature determination model; Using the glass transition temperature measurement model, the glass transition temperature of each training sample is obtained according to the preset correspondence between near-infrared spectral signals and glass transition temperatures. Based on the measured glass transition temperature and calibration glass transition temperature corresponding to each training sample, the glass transition temperature measurement model is iteratively trained to adjust the correspondence between the near-infrared spectral signal and the glass transition temperature, thereby obtaining a trained glass transition temperature measurement model.

3. The method according to claim 2, wherein, Before performing near-infrared spectroscopy tests on the multiple standard samples under multiple preset conditions and in the target environment, the method further includes: Obtain the boundary values ​​of the uncontrollable parameters corresponding to the target environment; The range of the uncontrollable parameter is determined based on its boundary values. Based on the value range of the uncontrollable parameter, a plurality of preset conditions are designed, including test conditions corresponding to the boundary values ​​of the uncontrollable parameter and test conditions corresponding to at least one intermediate value of the uncontrollable parameter.

4. The method according to claim 2, wherein, Before performing near-infrared spectroscopy tests on the multiple standard samples under multiple preset conditions and in the target environment, the method further includes: Obtain the boundary values ​​of the uncontrollable product parameters corresponding to the standard sample in the target production line; The value range of the uncontrollable product parameter is determined based on its boundary values. Based on the value range of the uncontrollable product parameter, the plurality of standard samples are prepared, including standard samples corresponding to the boundary values ​​of the uncontrollable product parameter and at least one standard sample corresponding to the intermediate value of the uncontrollable product parameter.

5. The method according to claim 2, wherein, The process of obtaining the calibrated glass transition temperature of the target polymer in each standard sample includes: The target glass transition temperature is determined by testing each standard sample using a target glass transition temperature determination method, wherein the target glass transition temperature determination method includes differential scanning calorimetry and / or dynamic mechanical analysis.

6. The method according to claim 1, wherein, The wavelength for the near-infrared spectroscopy test is 780 nm to 2526 nm.

7. The method according to any one of claims 1-6, wherein, The target polymer includes thermosetting polymers and / or thermoplastic polymers.

8. A method for testing glass transition temperature, comprising: Near-infrared spectroscopy tests were performed on multiple standard samples under multiple preset conditions and in a target environment to obtain the near-infrared spectral signal of each standard sample under each preset condition. The multiple preset conditions included test conditions designed based on uncontrollable parameters corresponding to the target environment, and the uncontrollable parameters included environmental parameters. The target environment was a fixed test environment designed based on controllable parameters of an industrial production site. The multiple standard samples contained a target polymer and included multiple standard samples with a fixed product structure and different uncontrollable product parameters designed based on controllable structural parameters and uncontrollable product parameters of the material and / or product. The uncontrollable product parameters included at least one of color, raw material ratio of the target polymer, moisture content, composite material parameters of the target polymer, and composite material structural parameters. Obtain the calibration glass transition temperature of the target polymer in each standard sample; Training samples are created by taking the near-infrared spectral signal of each standard sample under each preset condition and the calibration glass transition temperature of the standard sample, thus obtaining a training sample set. The training sample set is input into the glass transition temperature determination model; Using the glass transition temperature measurement model, the glass transition temperature of each training sample is obtained according to the preset correspondence between near-infrared spectral signals and glass transition temperatures. Based on the measured glass transition temperature and calibration glass transition temperature corresponding to each training sample, the glass transition temperature measurement model is iteratively trained to adjust the correspondence between the near-infrared spectral signal and the glass transition temperature, thereby obtaining a trained glass transition temperature measurement model.

9. The method according to claim 8, wherein, Before performing near-infrared spectroscopy tests on the multiple standard samples under multiple preset conditions and in the target environment, the method further includes: Obtain the boundary values ​​of the uncontrollable parameters corresponding to the target environment; The range of the uncontrollable parameter is determined based on its boundary values. Based on the value range of the uncontrollable parameter, a plurality of preset conditions are designed, including test conditions corresponding to the boundary values ​​of the uncontrollable parameter and test conditions corresponding to at least one intermediate value of the uncontrollable parameter.

10. The method according to claim 8, wherein, Before performing near-infrared spectroscopy tests on the multiple standard samples under multiple preset conditions and in the target environment, the method further includes: Obtain the boundary values ​​of the uncontrollable product parameters corresponding to the standard sample in the target production line; The value range of the uncontrollable product parameter is determined based on its boundary values. Based on the value range of the uncontrollable product parameter, the plurality of standard samples are prepared, including standard samples corresponding to the boundary values ​​of the uncontrollable product parameter and at least one standard sample corresponding to the intermediate value of the uncontrollable product parameter.

11. The method according to claim 8, wherein, The process of obtaining the calibrated glass transition temperature of the target polymer in each standard sample includes: The target glass transition temperature is determined by testing each standard sample using a target glass transition temperature determination method, wherein the target glass transition temperature determination method includes differential scanning calorimetry and / or dynamic mechanical analysis.

12. The method according to claim 8, wherein, The method further includes iteratively training the glass transition temperature measurement model based on the measured and calibrated glass transition temperatures corresponding to each training sample to adjust the correspondence between the near-infrared spectral signal and the glass transition temperature, and obtaining a trained glass transition temperature measurement model. Near-infrared spectroscopy is performed on the test object in the target environment to obtain the near-infrared spectral signal of the test object, wherein the test object includes the test material and / or product, and the test object contains the target polymer; The near-infrared spectral signal of the object to be tested is input into the trained glass transition temperature determination model; Using the trained glass transition temperature model, and based on the correspondence between the near-infrared spectral signal and the glass transition temperature, the measurement glass transition temperature corresponding to the near-infrared spectral signal of the object under test is determined.

13. The method according to claim 8, wherein, The wavelength for the near-infrared spectroscopy test is 780 nm to 2526 nm.

14. The method according to any one of claims 1-13, wherein, The target polymer includes thermosetting polymers and / or thermoplastic polymers.

15. A glass transition temperature testing device, characterized in that, include: The testing module is used to perform near-infrared spectroscopy testing on the test object in a target environment to obtain the near-infrared spectral signal of the test object, wherein the test object includes the test material and / or product, and the test object contains a target polymer; An input module is used to input the near-infrared spectral signal of the object under test into a pre-trained glass transition temperature (GLT) determination model. The GLT determination model is trained using a training sample set. The training sample set includes multiple training samples. Each training sample includes multiple near-infrared spectral signals obtained by performing near-infrared spectral tests on multiple standard samples under multiple preset conditions in the target environment, and multiple GLT labels corresponding to each of the multiple near-infrared spectral signals. The multiple preset conditions include test conditions designed based on uncontrollable parameters corresponding to the target environment, including environmental parameters. The multiple standard samples contain the target polymer and include multiple standard samples with different uncontrollable product parameters, including at least one of color, raw material ratio of the target polymer, moisture content, composite material parameters of the target polymer, and composite material structural parameters. The GLT label is the calibrated GLT of the target polymer in the standard sample corresponding to the near-infrared spectral signal. The determination module is used to determine the measurement glass transition temperature corresponding to the near-infrared spectral signal of the object under test by using the trained glass transition temperature model and according to the correspondence between the near-infrared spectral signal and the glass transition temperature.

16. A glass transition temperature testing device, comprising: The testing module is used to perform near-infrared spectroscopy tests on multiple standard samples under multiple preset conditions and in a target environment, respectively, to obtain the near-infrared spectral signal of each standard sample under each preset condition; the multiple preset conditions include test conditions designed according to uncontrollable parameters corresponding to the target environment, the uncontrollable parameters including environmental parameters; the target environment is a fixed test environment designed according to controllable parameters of an industrial production site; the multiple standard samples contain a target polymer, and the multiple standard samples include multiple standard samples with a fixed product structure designed according to controllable structural parameters and uncontrollable product parameters of materials and / or products, and having different uncontrollable product parameters, the uncontrollable product parameters including at least one of color, raw material ratio of the target polymer, moisture content, composite material parameters of the target polymer, and composite material structural parameters; The acquisition module is used to acquire the calibration glass transition temperature of the target polymer in each standard sample; A creation module is used to create training samples by taking the near-infrared spectral signal of each standard sample under each preset condition and the calibration glass transition temperature corresponding to the standard sample, thereby obtaining a training sample set. The input module is used to input the training sample set into the glass transition temperature determination model; The processing module is used to obtain the glass transition temperature of each training sample by means of the glass transition temperature measurement model and according to the preset correspondence between near-infrared spectral signals and glass transition temperatures. The training module is used to iteratively train the glass transition temperature measurement model based on the measured glass transition temperature and the calibrated glass transition temperature corresponding to each training sample, so as to adjust the correspondence between the near-infrared spectral signal and the glass transition temperature, and obtain the trained glass transition temperature measurement model.

17. An electronic device, characterized in that, The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the glass transition temperature testing method as described in any one of claims 1-14.

18. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, implement the glass transition temperature testing method as described in any one of claims 1-14.

19. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device causes the electronic device to perform the glass transition temperature testing method as described in any one of claims 1-14.

Images