A temperature monitoring system, temperature monitoring method and application based on a thermoresponsive cholesteric liquid crystal elastomer

Abstract

The present invention discloses a temperature monitoring system, a temperature monitoring method and an application based on a thermoresponsive cholesteric liquid crystal elastomer. The temperature monitoring system includes a cholesteric liquid crystal elastomer film, an imaging device and a processor, or includes a plurality of cholesteric liquid crystal elastomer films, an imaging device, an infrared imaging device and a processor. The present invention combines the optical color-changing property of the cholesteric liquid crystal elastomer film with machine vision technology, and monitors the temperature value (color-based temperature detection model) or temperature distribution map (color array-based temperature mapping model) of the object to be monitored through the color change of the cholesteric liquid crystal elastomer film. Moreover, through experimental verification, this monitoring method can achieve high-precision temperature monitoring in the range of 50-70 °C.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature monitoring, and in particular, to a temperature monitoring system, a temperature monitoring method and an application based on a thermoresponsive cholesteric liquid crystal elastomer. Background Art

[0002] With the acceleration of the modern industrialization process, temperature monitoring plays an increasingly important role in many fields. Especially in industries such as electronic devices, manufacturing, chemical engineering and medical treatment, real-time monitoring of temperature changes can effectively prevent equipment failures and material aging.

[0003] Existing temperature measurement devices, such as infrared temperature measurement devices and temperature sensors, although they can achieve temperature detection, often have problems such as high cost, complex installation and potential safety hazards caused by the devices themselves. In addition, various traditional thermometers cannot visually display temperature changes, and have a slow response speed when the ambient temperature changes rapidly.

[0004] In recent years, temperature-responsive materials (such as liquid crystal elastomers, shape memory polymers, etc.) have gradually become a research hotspot in temperature monitoring. Some physical or chemical properties of these materials change significantly with temperature, and thus can be used for temperature detection. However, in the prior art, the application of temperature-responsive materials is still restricted, especially in the problem of effectively correlating the color change of the materials with the ambient temperature, and there is no mature method to achieve high-precision temperature monitoring. Summary of the Invention

[0005] Based on this, the present invention provides a temperature monitoring system, a temperature monitoring method and an application based on a thermoresponsive cholesteric liquid crystal elastomer, and realizes the visualization of the temperature change feedback of the monitored object through the color change of the cholesteric liquid crystal elastomer film.

[0006] In the first aspect, the present invention provides a temperature monitoring system based on a thermoresponsive cholesteric liquid crystal elastomer, including:

[0007] A cholesteric liquid crystal elastomer film for characterizing the temperature change of the monitored object according to its own color change;

[0008] An imaging device for capturing the color change of the cholesteric liquid crystal elastomer film and forming an optical image;

[0009] A processor for receiving the optical image and inputting the optical image into a trained color-based temperature detection model for processing to output the temperature value under the corresponding conditions.

[0010] In the second aspect, the present invention provides a temperature monitoring method for a temperature monitoring system based on a thermoresponsive cholesteric liquid crystal elastomer, including the following steps:

[0011] Step S11, place the cholesteric liquid crystal elastomer film on the surface of the object to be monitored;

[0012] Step S12, use an imaging device to capture the color change of the cholesteric liquid crystal elastomer film and form an optical image;

[0013] Step S13, receive the optical image through a processor, and input the optical image into a trained color-based temperature detection model for processing to output the temperature value under corresponding conditions.

[0014] Furthermore, in the step S13, the construction of the color-based temperature detection model includes the following steps:

[0015] Step S131, place a red cholesteric liquid crystal elastomer film that is to be uniaxially stretched and maintained in a stretched state in an oven and bake it until the dynamic covalent bonds are completely exchanged, then take out the cholesteric liquid crystal elastomer film from the oven and cool it to room temperature, and cut it into blue sample films;

[0016] Step S132, place the blue sample film on a hot stage, within a preset time, use an imaging device to capture the color change of the blue sample film to generate an optical image, and preprocess the optical image to form an RGB image, and at the same time form a first temperature label file with the recorded corresponding temperature conditions;

[0017] Step S133, use a convolutional neural network architecture to establish a color-based temperature detection model, and input the first temperature label file into the color-based temperature detection model for iterative training;

[0018] Step S134, continuously optimize the parameters of the color-based temperature detection model through a loss function, and at the same time evaluate the performance of the color-based temperature detection model through a validation set, and adjust the hyperparameters of the color-based temperature detection model according to the evaluation results to achieve an optimal color-based temperature detection model.

[0019] Furthermore, in step S134, the loss function is the mean squared error loss function, and in the optimal color-based temperature detection model, the learning rate is 0.0005, the batch size is 16, and the number of training epochs is 100.

[0020] In a third aspect, the present invention provides a temperature monitoring system based on a thermoresponsive cholesteric liquid crystal elastomer, including:

[0021] A plurality of cholesteric liquid crystal elastomer films, and the plurality of cholesteric liquid crystal elastomer films are pasted on black oil paper in a pixel array manner for characterizing the temperature change of the object to be monitored according to their own color changes;

[0022] An imaging device for capturing the color change of the cholesteric liquid crystal elastomer film and forming an optical image;

[0023] An infrared imaging device for capturing the color change of the cholesteric liquid crystal elastomer film and forming an infrared temperature image under the conditions corresponding to the optical image;

[0024] A processor for receiving the optical image and the infrared temperature image, and inputting the optical image into a trained temperature mapping model based on a color array for processing to output a temperature distribution map under corresponding conditions.

[0025] In a fourth aspect, the present invention provides a temperature monitoring method for a temperature monitoring system based on a thermoresponsive cholesteric liquid crystal elastomer, including the following steps:

[0026] Step S21: After pasting a plurality of cholesteric liquid crystal elastomer films on black oil paper in a pixel array manner to form an array film, place the array film on the surface of the object to be monitored;

[0027] Step S22: Use an imaging device to capture the color change of the cholesteric liquid crystal elastomer film and form an optical image;

[0028] Step S23: Use an infrared imaging device to capture the color change of the cholesteric liquid crystal elastomer film and form an infrared temperature image under the conditions corresponding to the optical image;

[0029] Step S24: Receive the optical image and the infrared temperature image through a processor, and input the optical image and the infrared temperature image into a trained temperature mapping model based on a color array for processing to output a temperature distribution map under corresponding conditions.

[0030] Further, in the step S24, the construction of the temperature mapping model based on a color array includes the following steps:

[0031] Step S241: After placing a red cholesteric liquid crystal elastomer film that has been uniaxially stretched and maintained in a stretched state in an oven for baking until the dynamic covalent bonds are completely exchanged, take the cholesteric liquid crystal elastomer film out of the oven and cool it to room temperature, and paste the cut green sample film on black oil paper in a pixel array manner to form an array film;

[0032] Step S242: Place the array film on a glass plate, heat different positions with an open flame source, within a preset time, use an imaging device to capture the color change of the heated area of the array film to generate an optical image, and preprocess the optical image to form an RGB image;

[0033] Step S243: Use an infrared imaging device to capture the color change of the array film and form an infrared temperature image under the conditions corresponding to the optical image.

[0034] Step S244: Establish a temperature mapping model based on the color array using a generative adversarial neural network architecture, and input the second temperature label file formed by the RGB image and the infrared temperature image into the temperature mapping model based on the color array for iterative training.

[0035] Step S245: Continuously optimize the parameters of the temperature mapping model based on the color array through a loss function. At the same time, evaluate the performance of the temperature mapping model based on the color array through a validation set, and adjust the hyperparameters of the temperature mapping model based on the color array according to the evaluation results to achieve the optimal temperature mapping model based on the color array.

[0036] Further, in step S245, the loss function is the binary cross-entropy loss function. In the optimal temperature mapping model based on the color array, the generator learning rate is 0.00005, the discriminator learning rate is 0.000005, the batch size is 16, and the number of training epochs is 100.

[0037] Further, the preparation method of the cholesteric liquid crystal elastomer film includes the following steps:

[0038] Step S31: Add a thermoresponsive liquid crystal monomer, a chiral dopant, a crosslinking agent, a photoinitiator, a dynamic covalent bond, and a catalyst to an organic solvent according to a preset mass ratio for dissolution to form a precursor solution. Among them, the mass ratio of the thermoresponsive liquid crystal monomer, chiral dopant, crosslinking agent, photoinitiator, dynamic covalent bond, and catalyst is: 1107 mg: 46 mg: 270 mg: 10 mg: 136 mg: 3 mg.

[0039] Step S32: Pour the precursor solution into a mold and let it stand. After the evaporation of the organic solvent and the formation of the cholesteric phase, it is placed under ultraviolet light for curing to obtain a fully crosslinked cholesteric liquid crystal elastomer film.

[0040] Step S33: Perform uniaxial stretching on the cholesteric liquid crystal elastomer film, and maintain the stretched state at a preset temperature for a preset time to complete the dynamic covalent bond exchange, so that the initial red cholesteric liquid crystal elastomer film is oriented along the stretching direction and changes to the corresponding color.

[0041] Fifth aspect, the present invention provides an application of a temperature monitoring system based on a thermoresponsive cholesteric liquid crystal elastomer in monitoring the surface temperature of an electronic device.

[0042] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0043] First, the preparation process of the cholesteric liquid crystal elastomer film used in the temperature monitoring system of the present invention is simple, the reaction conditions are mild, and it is easy to be industrially produced.

[0044] Second, the present invention realizes the visualization of the temperature change feedback of the monitored object through the color change of the cholesteric liquid crystal elastomer film, greatly enhancing the usability and intuitiveness of the monitoring system.

[0045] Third, compared with traditional infrared temperature monitoring devices, temperature sensors and thermometers, the temperature monitoring method in the present invention has the advantages of low cost, simple structure and high adaptability, and can be cut into various shapes as needed. Description of the Drawings

[0046] Figure 1 Schematic diagram of the preliminary temperature detection using the CLCE film in Example 1.

[0047] Figure 2 Schematic diagram of the process for realizing the temperature detection function based on CLCE and machine vision technology in Example 1 and Comparative Example 1, and schematic diagram of the network architecture of the color-based temperature detection model (CTPM).

[0048] Figure 3 Loss curve (left) and training result evaluation curve (right) of the color-based temperature detection model (CTPM) obtained in Example 1.

[0049] Figure 4 Results of temperature detection by combining the CLCE film and the color-based temperature detection model (CTPM) obtained in Example 1, where T t represents the actual temperature value under the corresponding conditions, and T p represents the detected temperature value output by the model (scale: 2 cm).

[0050] Figure 5 Schematic diagram of the change of the blue CLCE film obtained in Comparative Example 1 during heating (scale: 2 cm).

[0051] Figure 6 Loss curve (left) and training result evaluation curve (right) of the color-based temperature detection model (CTPM) obtained in Comparative Example 1.

[0052] Figure 7 Schematic diagram of the process for preparing the CLCE array in Example 2.

[0053] Figure 8 Schematic diagram of the network structure of the color array temperature mapping model (CATMM) obtained in Example 2.

[0054] Figure 9Loss curves of the generator (left) and discriminator (right) during the model training process in Example 2.

[0055] Figure 10 Schematic diagram of the process for simulating the use of a CLCE array to monitor the surface temperature of a locally high-temperature object in Example 2.

[0056] Figure 11 Results of the temperature monitoring obtained in Example 2 (scale bar: 2 cm).

[0057] Figure 12 Results of the temperature monitoring under the condition of high temperature at different positions in Example 2 (scale bar: 2 cm). Detailed implementation manners

[0058] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments in the following description are only examples, and those skilled in the art can think of other obvious variations.

[0059] In a first aspect, the present invention provides a temperature monitoring system based on a thermoresponsive cholesteric liquid crystal elastomer, including:

[0060] A cholesteric liquid crystal elastomer film for characterizing the temperature change of the object to be monitored according to its own color change;

[0061] An imaging device for capturing the color change of the cholesteric liquid crystal elastomer film and forming an optical image;

[0062] A processor for receiving the optical image and inputting the optical image into a trained color-based temperature detection model for processing to output the temperature value under the corresponding conditions.

[0063] In a second aspect, the present invention provides a temperature monitoring method for a temperature monitoring system based on a thermoresponsive cholesteric liquid crystal elastomer, including the following steps:

[0064] Step S11: Place the cholesteric liquid crystal elastomer film on the surface of the object to be monitored;

[0065] Step S12: Use an imaging device to capture the color change of the cholesteric liquid crystal elastomer film and form an optical image;

[0066] Step S13: Receive the optical image through a processor and input the optical image into a trained color-based temperature detection model for processing to output the temperature value under the corresponding conditions.

[0067] Further, in the step S13, the construction of the color-based temperature detection model includes the following steps:

[0068] Step S131: After placing the red cholesteric liquid crystal elastomer film that is to be uniaxially stretched and maintained in a stretched state in an oven for baking until the dynamic covalent bonds are completely exchanged, take out the cholesteric liquid crystal elastomer film from the oven and cool it to room temperature, and then cut it into blue sample films;

[0069] Step S132: Place the blue sample film on a hot stage. Within a preset time, capture the color change of the blue sample film through an imaging device to generate an optical image, and preprocess the optical image to form an RGB image, and at the same time form a first temperature label file with the recorded corresponding temperature conditions;

[0070] Specifically, in this step, the preprocessing includes rotation, cropping, and scaling, etc., to increase the diversity of data and improve the robustness of the model.

[0071] Step S133: Establish a color-based temperature detection model using a convolutional neural network architecture, and input the first temperature label file into the color-based temperature detection model for iterative training;

[0072] Specifically, before performing iterative training, it is necessary to initialize the model and set parameters.

[0073] Step S134: Continuously optimize the parameters of the color-based temperature detection model through a loss function, and at the same time evaluate the performance of the color-based temperature detection model through a validation set, and adjust the hyperparameters of the color-based temperature detection model according to the evaluation results to achieve an optimal color-based temperature detection model.

[0074] Furthermore, in Step S134, the loss function is the mean squared error loss function, and in the optimal color-based temperature detection model (CTPM), the learning rate is 0.0005, the batch size is 16, and the number of training epochs is 100.

[0075] In a third aspect, the present invention provides a temperature monitoring system based on a thermoresponsive cholesteric liquid crystal elastomer, including:

[0076] A plurality of cholesteric liquid crystal elastomer films, and the plurality of cholesteric liquid crystal elastomer films are pasted on black oil paper in a pixel array manner for characterizing the temperature change of the object to be monitored according to their own color changes;

[0077] An imaging device for capturing the color change of the cholesteric liquid crystal elastomer film and forming an optical image;

[0078] An infrared imaging device for capturing the color change of the cholesteric liquid crystal elastomer film and forming an infrared temperature image under the corresponding conditions of the optical image;

[0079] A processor, configured to receive the optical image and the infrared temperature image, and input the optical image into a trained temperature mapping model based on a color array for processing, so as to output a temperature distribution map under corresponding conditions.

[0080] In a fourth aspect, the present invention provides a temperature monitoring method for a temperature monitoring system based on a thermoresponsive cholesteric liquid crystal elastomer, including the following steps:

[0081] Step S21: After pasting a plurality of cholesteric liquid crystal elastomer thin films in a pixel array manner on a black oil paper to form an array film, place the array film on the surface of the object to be monitored.

[0082] Step S22: Use an imaging device to capture the color change of the cholesteric liquid crystal elastomer thin film and form an optical image.

[0083] Step S23: Use an infrared imaging device to capture the color change of the cholesteric liquid crystal elastomer thin film and form an infrared temperature image under the corresponding conditions of the optical image.

[0084] Step S24: Receive the optical image and the infrared temperature image through a processor, and input the optical image and the infrared temperature image into a trained temperature mapping model based on a color array for processing, so as to output a temperature distribution map under corresponding conditions.

[0085] Further, in step S24, the construction of the temperature mapping model based on a color array includes the following steps:

[0086] Step S241: After placing a uniaxially stretched and still stretched red cholesteric liquid crystal elastomer thin film in an oven and baking it until the dynamic covalent bonds are completely exchanged, take out the cholesteric liquid crystal elastomer thin film from the oven and cool it to room temperature, and paste the cut green sample thin film in a pixel array manner on a black oil paper to form an array film.

[0087] Step S242: Place the array film on a glass plate, heat different positions with an open flame source, within a preset time, use an imaging device to capture the color change of the heated area of the array film to generate an optical image, and preprocess the optical image to form an RGB image.

[0088] Specifically, in this step, the preprocessing includes rotation, cropping, scaling, etc., to increase the diversity of data and improve the robustness of the model.

[0089] Step S243: Use an infrared imaging device to capture the color change of the array film and form an infrared temperature image under the corresponding conditions of the optical image.

[0090] Step S244: Establish a temperature mapping model based on a color array using a generative adversarial neural network architecture, and input the second temperature label file formed by the RGB image and the infrared temperature image into the temperature mapping model based on the color array for iterative training;

[0091] Specifically, before iterative training, model initialization and parameter settings are required.

[0092] Step S245: Continuously optimize the parameters of the temperature mapping model based on the color array through a loss function, and at the same time evaluate the performance of the temperature mapping model based on the color array through a validation set, and adjust the hyperparameters of the temperature mapping model based on the color array according to the evaluation results to achieve the optimal temperature mapping model based on the color array.

[0093] Furthermore, in step S245, the loss function is the binary cross-entropy loss function, and in the optimal temperature mapping model based on the color array (CATMM, including a generator and a discriminator), the learning rate of the generator is 0.00005, the learning rate of the discriminator is 0.000005, the batch size is 16, and the number of training epochs is 100.

[0094] Furthermore, the preparation method of the cholesteric liquid crystal elastomer film includes the following steps:

[0095] Step S31: Add a thermoresponsive liquid crystal monomer, a chiral dopant, a crosslinking agent, a photoinitiator, a dynamic covalent bond, and a catalyst into an organic solvent according to a preset mass ratio for dissolution to form a precursor solution, wherein the mass ratio of the thermoresponsive liquid crystal monomer, the chiral dopant, the crosslinking agent, the photoinitiator, the dynamic covalent bond, and the catalyst is: 1107 mg: 46 mg: 270 mg: 10 mg: 136 mg: 3 mg;

[0096] Specifically, in this step, the thermoresponsive liquid crystal monomer is RM257, the chiral dopant is LC756, the crosslinking agents are pentaerythritol tetra(3-mercaptopropionate) (PETMP) and 2,2′-(1,2-ethylenedioxy)bis(ethanethiol) (EDDET), the photoinitiator is benzoin dimethyl ether (HHMP), the dynamic covalent bond is a thermally exchangeable borate bond (BDB), the catalyst is di-n-propylamine (DPA), and it is diluted in toluene at a ratio of 1:50 when used.

[0097] Furthermore, the organic solvent is toluene, the concentrations of the thermoresponsive liquid crystal monomer and the chiral dopant in the precursor solution are 50%-60%, the dissolution temperature is about 80 °C, the stirring speed during dissolution is 300-400 r / min, and the stirring time is 10-15 min.

[0098] Step S32: Pour the precursor solution into a mold and let it stand still. After the evaporation of the organic solvent and the formation of the cholesteric phase, place it under ultraviolet light for curing to obtain a fully cross-linked cholesteric liquid crystal elastomer film.

[0099] Specifically, in this step, the cavity size in the mold is 20mm×40mm×0.5mm, the environmental temperature for the evaporation of the organic solvent and the formation of the cholesteric phase is room temperature, and the time is 20 - 24h. The conditions for ultraviolet light curing are: ultraviolet light wavelength 365nm, ultraviolet light power 20 - 30mW / cm 2 , and the light irradiation time is 10 - 15min.

[0100] Step S33: Perform uniaxial stretching on the cholesteric liquid crystal elastomer film and maintain the stretched state for a preset time under preset temperature conditions to complete the dynamic covalent bond exchange, so that the initial red cholesteric liquid crystal elastomer film is oriented along the stretching direction and changes to the corresponding color.

[0101] Specifically, in this step, the preset temperature conditions are 70 - 75°C, and the preset time is 2 - 6h.

[0102] Furthermore, manually cut the cholesteric elastomer film oriented along the stretching direction into the required shape and size, or combine them for later use.

[0103] In the fifth aspect, the present invention provides an application of a temperature monitoring system based on a thermoresponsive cholesteric liquid crystal elastomer in monitoring the surface temperature of an electronic device.

[0104] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0105] First, the preparation process of the cholesteric liquid crystal elastomer film used in the temperature monitoring system of the present invention is simple, the reaction conditions are mild, and it is easy to be industrially produced.

[0106] Second, the present invention realizes the visualization of the temperature change feedback of the monitored object through the color change of the cholesteric liquid crystal elastomer film, greatly enhancing the usability and intuitiveness of the monitoring system.

[0107] Third, compared with traditional infrared temperature monitoring devices, temperature sensors and thermometers, the temperature monitoring method in the present invention has the advantages of low cost, simple structure and high adaptability, and can be cut into various shapes as needed.

[0108] In the embodiments of the present invention, those not specified in specific conditions are used according to conventional conditions or the conditions recommended by the manufacturer. All raw materials, reagents, etc. not specified by the manufacturer are conventional products that can be obtained through commercial purchase.

[0109] In the examples and comparative examples of the present invention, the dynamic covalent bonds (BDB) contained in the cholesteric liquid crystal elastomer film (CLCE) were prepared by the following method:

[0110] Dissolve 2.0 g of 1-thioglycerol and 1.5 g of 1,4-benzenediboronic acid in 40 ml of tetrahydrofuran, then add 4.0 g of anhydrous magnesium sulfate and 0.1 g of distilled water. The mixture was stirred at room temperature for 24 h under a sealed environment. Subsequently, magnesium sulfate was removed by vacuum filtration, and the solvent was evaporated in an oven at 80 °C for 12 h. The resulting solid was washed 3-4 times with n-hexane to remove excess 1-thioglycerol. Finally, the solid was dried at 80 °C for 4 h to obtain a white solid, which was then ground into powder for later use.

[0111] The initial red-reflecting CLCE was prepared by the following method:

[0112] Mix 1107.0 mg of RM257 and 46.0 mg of LC756 with 400 mg of toluene under heating and stirring for 10 min. Then, add 81.6 mg of crosslinker pentaerythritol tetrakis(3-mercaptopropionate) (PETMP), 188.4 mg of 2,2′-(1,2-ethylenedioxy)bis(ethanethiol) (EDDET), 136.0 mg of dynamic covalent bond (BDB), 10.0 mg of photoinitiator benzoin dimethyl ether (HHMP), and 150 mg of catalyst dipropylamine (DPA) (diluted in toluene at a ratio of 1:50) to the solution. The solution was stirred at 60 °C for 10 min and sonicated for 1 min. Then, the precursor solution was poured into a mold (20 mm × 40 mm × 0.5 mm), placed in a fume hood, and reacted in a light-shielded environment until a cholesteric phase was formed and the solvent was completely evaporated. After that, the cholesteric liquid crystal was exposed to ultraviolet light at 365 nm and 20 mW / cm² for 10 min to obtain a fully crosslinked CLCE film. Examples

[0113] (1) Uniaxially stretch the red cholesteric liquid crystal elastomer film with a tensile strain of 60%, keep the stretched state and place the film in an oven at 70 °C. After about 2 h, when the dynamic bonds are completely exchanged, take the film out of the oven and cool it to room temperature. This process causes the initial red CLCE film to be oriented along the stretching direction and turn green. Cut the film into a rectangular film of 10 mm × 20 mm for later use.

[0114] (2) Place the above green film on a hot stage at 100 °C. The film will change back from green to red within 10 s. This process is captured using a smartphone or digital camera to generate an optical image, and the corresponding temperature conditions are recorded to form a label file and a training dataset for subsequent model training.

[0115] (3)A color-based temperature detection model (CTPM) was established based on the convolutional neural network (CNN) architecture. The specific model network architecture is shown in Table 1. Based on the loss curve and output results generated during the training process, the parameters of the model training and the training dataset were continuously adjusted. After multiple training attempts, when the learning rate was 0.0005, the batch size was 16, and the number of training epochs was 100, a better training effect could be achieved.

[0116]

[0117] (4)The trained model will be used to identify the CLCE and output the temperature value under the corresponding conditions according to its color. The CLCE film is placed on a high-temperature surface, and the temperature range of the object surface is initially judged by observing its color change. Then, an image is taken by a smartphone or a digital camera and input into the above-trained model, and the model will output the accurate temperature value under the corresponding conditions according to the input image. The above process realizes the temperature detection function.

[0118] (5)After the temperature detection is completed, the CLCE film will automatically return to its original color for future use.

[0119] Figure 1 It is the preliminary temperature detection function realized by the CLCE film prepared in Example 1, and the approximate temperature of a certain object surface can be initially judged according to its color. Red (left) represents high temperature danger on the object surface, while green (right) represents room temperature safety on the object surface.

[0120] Figure 2 It is the schematic flow chart of the temperature detection function realized based on CLCE and machine vision technology and the schematic network architecture of the color-based temperature detection model (CTPM) in Example 1.

[0121] Figure 3 and Figure 4 It is the training result of the model in Example 1, indicating that the training effect of the model is good, the temperature detection is accurate, and its accuracy rate is higher than 95% in the range of 50 - 70 °C.

[0122] (1)The red cholesteric liquid crystal elastomer film was uniaxially stretched with a strain of 120%, and the stretched state was maintained while the film was placed in an oven at 70 °C. After about 2 h, when the dynamic bonds were completely exchanged, the film was taken out of the oven and cooled to room temperature. This process caused the initial red CLCE film to be oriented along the stretching direction and turn blue. The film was cut into a rectangular film of 10 mm × 20 mm for future use.

[0123] (2) Place the above blue film on a hot stage at 100 °C. The film will change from blue to green within 10 s and finally back to red. This process is captured using a smartphone or digital camera to generate an optical image, and the corresponding temperature conditions are recorded to form a label file and a training dataset for subsequent model training.

[0124] (3) A color-based temperature detection model (CTPM) was established based on the convolutional neural network (CNN) architecture. The detailed model network architecture is shown in Table 1. Based on the loss curve and output results generated during the training process, the parameters of the model training and the training dataset are continuously adjusted. After multiple training attempts, when the learning rate is 0.0005, the batch size is 16, and the number of training epochs is 100, a better training effect can be achieved.

[0125] (4) The trained model will be used to identify the CLCE and output the temperature value under the corresponding conditions according to its color. Place the CLCE film on a high-temperature surface, initially judge the temperature range of the object surface by observing its color change, then take a picture with a smartphone or digital camera and input the image into the above-trained model. The model will output the accurate temperature value under the corresponding conditions according to the input image. The above process realizes the temperature detection function.

[0126] (5) After the temperature detection is completed, the CLCE film will automatically return to its original color for the next use.

[0127] Figure 5 It shows that the CLCE film will gradually change from blue to red as the temperature gradually increases. Figure 6 It indicates that the model training effect is good. Compared with the training results in Example 1, the training results in Comparative Example 1 are more excellent in the range of 50 - 70 °C. The reason is that the color change process of the film is different from that in Example 1, where it gradually changes from green to red. In Comparative Example 1, the color of the film will gradually change from blue to green and then to red as the temperature increases. Especially in the range of 50 - 70 °C, the image features given for machine vision recognition will be more obvious than those in Example 1, so a better training effect can be obtained. Example

[0128] (1) Uniaxially stretch the red cholesteric liquid crystal elastomer film with a tensile strain of 60%. Keep the stretched state and place the film in an oven at 70 °C. After about 2 h, when the dynamic bonds are completely exchanged, take the film out of the oven and cool it to room temperature. This process causes the initial red CLCE film to orient along the stretching direction and turn green. The film is cut into 2 mm × 2 mm "pixels", and the "pixels" are pasted on black oil paper using double-sided tape to form a 10 × 10 CLCE array.

[0129] (2) Place the above-mentioned array on a glass plate and heat different positions using an open flame source. Color changes will occur in the heated areas. The above process is captured using a smartphone or digital camera to generate an optical image, and an infrared camera is used to record the red temperature image under the corresponding conditions. The optical image and the corresponding infrared temperature image form a label file and a training dataset for subsequent model training.

[0130] (3) A color-array-based temperature mapping model (CATMM) is established based on the generative adversarial network (GAN) architecture. The model mainly includes two parts: a generator and a discriminator. Their specific network architectures are shown in Tables 2 and 3 respectively. Based on the loss curves and output results generated during the training process, the parameters of the model training and the training dataset are continuously adjusted. After multiple training attempts, when the learning rate of the generator is 0.00005, the learning rate of the discriminator is 0.000005, the batch size is 16, and the number of training epochs is 100, a better training effect can be achieved.

[0131]

[0132]

[0133] (4) The trained model will be used to identify CLCE and output the temperature distribution map under the corresponding conditions according to its color. Use a glass plate to simulate the surface of a high-temperature object, use an open flame source to heat to simulate the local high temperature of an object, place the CLCE array on the glass plate, and use a smartphone or digital camera to take pictures of the color change process. One frame of the video is taken every 15 s and input into the above-trained model, and the model will generate the corresponding temperature distribution image based on the input image. The above process realizes the temperature monitoring function.

[0134] (5) After the temperature monitoring is completed, the CLCE array will automatically return to its original color for future use. Replace the heating position of the open flame source in step (2) and conduct the monitoring again, and the ideal effect can also be obtained.

[0135] Figure 7 It is the flowchart for preparing the CLCE array in Example 2.

[0136] Figure 8 It is the schematic diagram of the network architecture of the color-array-based temperature mapping model (CATMM). Figure 9 It is the loss curve of the generator and the discriminator during the training process, and the curve results show that the training effect of the model is good.

[0137] Figure 10It is a schematic flow chart of simulating local high temperature on the surface of an object and using a CLCE array and a deep learning model for temperature monitoring. Figure 11 It is the comparison result of image capture every 15 s during the temperature monitoring process and the output of the temperature distribution image. Among them, the "real image" is the infrared temperature image under the corresponding conditions. The results show that the model can output a temperature distribution image that highly coincides with the infrared temperature image under the corresponding conditions, proving the accuracy of model recognition.

[0138] Figure 12 It is the result of temperature monitoring using a CLCE array under different local heating positions, indicating that the model has strong generalization ability.

[0139] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection required by the present invention is defined by the appended claims and their equivalents.

Claims

1. A temperature monitoring method for a temperature monitoring system based on a thermoresponsive cholesteric liquid crystal elastomer, characterized in that, The temperature monitoring system includes: A cholesteric liquid crystal elastomer film for characterizing the temperature change of the object to be monitored according to its own color change; An imaging device for capturing the color change of the cholesteric liquid crystal elastomer film and forming an optical image; A processor for receiving the optical image and inputting the optical image into a trained color-based temperature detection model for processing to output the temperature value under corresponding conditions; The temperature monitoring method includes the following steps: Step S11: Place the cholesteric liquid crystal elastomer film on the surface of the object to be monitored; Step S12: Use an imaging device to capture the color change of the cholesteric liquid crystal elastomer film and form an optical image; Step S13: Receive the optical image through a processor and input the optical image into a trained color-based temperature detection model for processing to output the temperature value under corresponding conditions; In the step S13, the construction of the color-based temperature detection model includes the following steps: Step S131: Place a red cholesteric liquid crystal elastomer film that is being uniaxially stretched and maintained in a stretched state in an oven and bake it until the dynamic covalent bonds are completely exchanged. Then take out the cholesteric liquid crystal elastomer film from the oven and cool it to room temperature, and cut it into a blue sample film; Step S132: Place the blue sample film on a hot stage. Within a preset time, use an imaging device to capture the color change of the blue sample film to generate an optical image, and preprocess the optical image to form an RGB image, and at the same time form a first temperature label file with the recorded corresponding temperature conditions; Step S133: Use a convolutional neural network architecture to establish a color-based temperature detection model, and input the first temperature label file into the color-based temperature detection model for iterative training; Step S134: Continuously optimize the parameters of the color-based temperature detection model through a loss function, and at the same time evaluate the performance of the color-based temperature detection model through a validation set, and adjust the hyperparameters of the color-based temperature detection model according to the evaluation results to achieve the optimal color-based temperature detection model.

2. The temperature monitoring method of the temperature monitoring system based on a thermoresponsive cholesteric liquid crystal elastomer according to claim 1, characterized in that, In step S134, the loss function is the mean squared error loss function, and in the optimal color-based temperature detection model, the learning rate is 0.0005, the batch size is 16, and the number of training epochs is 100.

3. The temperature monitoring method of the temperature monitoring system based on a thermoresponsive cholesteric liquid crystal elastomer according to claim 1, characterized in that, The preparation method of the cholesteric liquid crystal elastomer film includes the following steps: Step S31: Add a thermoresponsive liquid crystal monomer, a chiral dopant, a crosslinking agent, a photoinitiator, a dynamic covalent bond, and a catalyst to an organic solvent in a preset mass ratio for dissolution to form a precursor solution. Among them, the mass ratio of the thermoresponsive liquid crystal monomer, the chiral dopant, the crosslinking agent, the photoinitiator, the dynamic covalent bond, and the catalyst is: 1107 mg: 46 mg: 270 mg: 10 mg: 136 mg: 3 mg; Step S32: Pour the precursor solution into a mold and let it stand. After the organic solvent evaporates and the cholesteric phase is formed, place it under ultraviolet light for curing to obtain a fully crosslinked cholesteric liquid crystal elastomer film; Step S33: Perform uniaxial stretching on the cholesteric liquid crystal elastomer film, and maintain the stretched state to process for a preset time under preset temperature conditions to complete the dynamic covalent bond exchange, so that the initially red cholesteric liquid crystal elastomer film is oriented along the stretching direction and changes to the corresponding color.

4. A temperature monitoring method for a temperature monitoring system based on a thermoresponsive cholesteric liquid crystal elastomer, characterized in that, The temperature monitoring system includes: Multiple cholesteric liquid crystal elastomer films, which are pasted on the black oil paper in a pixel array manner and are used to characterize the temperature change of the monitored object according to their own color changes; An imaging device for capturing the color changes of the cholesteric liquid crystal elastomer film and forming an optical image; An infrared imaging device for capturing the color changes of the cholesteric liquid crystal elastomer film and forming an infrared temperature image corresponding to the optical image; A processor for receiving the optical image and the infrared temperature image, and inputting the optical image into a trained temperature mapping model based on the color array for processing to output a temperature distribution map under corresponding conditions; The temperature monitoring method includes the following steps: Step S21: After pasting multiple cholesteric liquid crystal elastomer films on the black oil paper in a pixel array manner to form an array film, place the array film on the surface of the object to be monitored; Step S22: Use an imaging device to capture the color changes of the cholesteric liquid crystal elastomer film and form an optical image; Step S23: Use an infrared imaging device to capture the color changes of the cholesteric liquid crystal elastomer film and form an infrared temperature image corresponding to the optical image; Step S24: Receive the optical image and the infrared temperature image through the processor, and input the optical image and the infrared temperature image into a trained temperature mapping model based on the color array for processing to output a temperature distribution map under corresponding conditions; In the step S24, the construction of the temperature mapping model based on the color array includes the following steps: Step S241: After placing the red cholesteric liquid crystal elastomer film that has been uniaxially stretched and maintained in the stretched state in an oven for baking until the dynamic covalent bonds are completely exchanged, take out the cholesteric liquid crystal elastomer film from the oven and cool it to room temperature, and cut it into green sample films and paste them on the black oil paper in a pixel array manner to form an array film; Step S242: Place the array film on a glass plate, heat different positions with an open flame source, and within a preset time, use an imaging device to capture the color changes of the heated area of the array film to generate an optical image, and preprocess the optical image to form an RGB image; Step S243: Use an infrared imaging device to capture the color changes of the array film and form an infrared temperature image corresponding to the optical image; Step S244: Establish a temperature mapping model based on the color array using the generative adversarial neural network architecture, and input the second temperature label file formed by the RGB image and the infrared temperature image into the temperature mapping model based on the color array for iterative training; Step S245: Continuously optimize the parameters of the temperature mapping model based on the color array through the loss function. At the same time, evaluate the performance of the temperature mapping model based on the color array through the validation set, and adjust the hyperparameters of the temperature mapping model based on the color array according to the evaluation results to achieve the optimal temperature mapping model based on the color array.

5. The temperature monitoring method of the temperature monitoring system based on a thermoresponsive cholesteric liquid crystal elastomer according to claim 4, characterized in that, In step S245, the loss function is the binary cross-entropy loss function. In the optimal temperature mapping model based on the color array, the generator learning rate is 0.00005, the discriminator learning rate is 0.000005, the batch size is 16, and the number of training epochs is 100.

6. The temperature monitoring method of the temperature monitoring system based on a thermoresponsive cholesteric liquid crystal elastomer according to claim 4, characterized in that, The method for preparing the cholesteric liquid crystal elastomer film includes the following steps: Step S31: Add a thermoresponsive liquid crystal monomer, a chiral dopant, a crosslinking agent, a photoinitiator, a dynamic covalent bond, and a catalyst into an organic solvent according to a preset mass ratio for dissolution to form a precursor solution. Among them, the mass ratio of the thermoresponsive liquid crystal monomer, the chiral dopant, the crosslinking agent, the photoinitiator, the dynamic covalent bond, and the catalyst is: 1107 mg: 46 mg: 270 mg: 10 mg: 136 mg: 3 mg; Step S32: Pour the precursor solution into a mold and let it stand. After the evaporation of the organic solvent and the formation of the cholesteric phase, place it under ultraviolet light for curing to obtain a fully crosslinked cholesteric liquid crystal elastomer film; Step S33: Perform uniaxial stretching treatment on the cholesteric liquid crystal elastomer film, and maintain the stretched state and treat it for a preset time under preset temperature conditions to complete the dynamic covalent bond exchange, so that the initial red cholesteric liquid crystal elastomer film is oriented along the stretching direction and changes to the corresponding color.

7. Application of the temperature monitoring method of the temperature monitoring system based on the thermoresponsive cholesteric liquid crystal elastomer according to claim 1 or 4 in monitoring the surface temperature of an electronic device.

Images