Vienna stability test system and its stability determination method

Abstract

This application relates to the technical field of gunpowder stability testing and provides a Vienna stability test system and a stability determination method thereof. The Vienna stability test system includes a stability test device, a camera device, a gas detection device, and a stability determination device. The gas detection device is used to detect the gas concentration generated by a second sample; the camera device is used to capture multiple images of Vienna test paper in a first test beaker; and the stability determination device is used to input the multiple test paper images into a trained image recognition model. The image recognition model identifies the color of each test paper image and outputs a determination result when the color of the test paper image is identified as the endpoint color. Based on the determination result and the gas concentration, the reaction degree of the second sample when the color of the Vienna test paper changes to the endpoint color is quantitatively determined. The present application can automatically identify the endpoint color of the Vienna test paper, thereby improving the accuracy of the stability test results.

Description

Technical Field

[0001] The present application relates to the technical field of gunpowder stability testing, and in particular to a Vienna stability test system and a stability determination method thereof. Background Art

[0002] The Vienna stability test is a classic method for testing the stability of explosives, nitrocellulose, and other materials in China. Proposed by the Frenchman Vieille in 1896, the method involves placing a fixed amount of sample and a certain size of Vienna paper (such as litmus paper) into a test tube. The test tube is heated at 106.5°C (degrees Celsius). The temperature is recorded every 15 minutes, and the color change of the Vienna paper is recorded every 30 minutes. The total time it takes for the Vienna paper to turn red indicates the stability of the sample.

[0003] The existing stability testing process relies on operators visually observing and judging color. However, the color of the Vienna test paper can change in various ways during the sample reaction process. Furthermore, the closer the sample reaction approaches the endpoint of "red," the closer the color of the Vienna test paper becomes to the same color scheme, making it easy to misjudge the endpoint. Furthermore, different operators can produce different color judgment errors, which in turn affects the accuracy of stability test results. Summary of the Invention

[0004] In view of this, the embodiments of the present application provide a Vienna stability test system and a stability determination method thereof to solve the problem in the prior art that the determination of the endpoint "red" of the Vienna test paper always relies on human visual experience, which affects the accuracy of the stability test results.

[0005] A first aspect of an embodiment of the present application provides a Vienna stability test system, comprising: a stability test device, a camera device, a gas detection device, and a stability determination device;

[0006] The stability test apparatus includes a stability tester, a first test beaker, and Vienna test paper; the gas detection apparatus includes a second test beaker and a gas sensor; the stability tester is provided with a peep window, the first test beaker and the second test beaker are both placed in the stability tester, the Vienna test paper is placed in the first test beaker, and the gas sensor is placed in the second test beaker, with the first test beaker positioned directly opposite the peep window; the first test beaker is used to place a first sample, and the second test beaker is used to place a second sample of the same type and quality as the first sample; the stability test apparatus is used to perform stability tests on the first and second samples; the gas detection apparatus is used to detect the gas concentration generated by the second sample during the simultaneous stability test of the first and second samples, and transmit the gas concentration to the stability determination apparatus;

[0007] The camera device is located outside the stability tester and directly opposite the peep window. The camera device is used to capture multiple test paper images of the Vienna test paper in the first test beaker during the synchronous stability test of the first sample and the second sample, and transmit the multiple test paper images to the stability determination device.

[0008] The stability judgment device is used to receive multiple test paper images and input the multiple test paper images into a trained image recognition model, identify the color of each test paper image through the image recognition model, and output a judgment result when the color of the test paper image is recognized as the endpoint color. It is also used to quantitatively judge the reaction degree of the second sample when the color of the Vienna test paper changes to the endpoint color based on the judgment result and the gas concentration.

[0009] A second aspect of the embodiments of the present application provides a method for determining the stability of a Vienna stability test system, which is applied to the device for determining the stability of the Vienna stability test system as described in the first aspect. The method includes:

[0010] During a stability test of a first sample, receiving a plurality of test paper images of Vienna test paper in a first test beaker captured by a camera device;

[0011] Input multiple test strip images into a trained image recognition model, identify the color of each test strip image through the image recognition model, and output the discrimination result when the color of the test strip image is identified as the endpoint color;

[0012] According to the discrimination result and the gas concentration, the reaction degree of the second sample when the color of the Vienna test paper changes to the end point color is quantitatively judged.

[0013] Compared with the prior art, the embodiments of the present application have the following beneficial effects: by providing a stability testing device, a camera device, a gas detection device and a stability judgment device, the stability testing device is used to perform a stability test on the first sample and the second sample; the gas detection device is used to detect the gas concentration generated by the second sample during the synchronous stability test of the first sample and the second sample, and send the gas concentration to the stability judgment device; the camera device is used to collect multiple test paper images of the Vienna test paper in the first test beaker during the synchronous stability test of the first sample and the second sample, and send the multiple test paper images to the stability judgment device; the stability judgment device is used to receive the multiple test paper images, and input the multiple test paper images into a trained image recognition model, and identify the color of each test paper image through the image recognition model. When the color of the test paper image is identified as the endpoint color, the judgment result is output, and the device is used to quantitatively judge the reaction degree of the second sample when the color of the Vienna test paper changes to the endpoint color based on the judgment result and the gas concentration. The above-mentioned technical means can not only realize the automatic recognition of the endpoint color of the Vienna test paper, thereby replacing the long-standing method of using the human eye to judge the endpoint color and improving the accuracy of the stability test results, but also, by monitoring the gas concentration generated by the sample during the test, it is possible to more intuitively obtain the reaction depth reached by the sample when the color of the Vienna test paper changes to the endpoint color, thereby quantifying the sample reaction process and providing a certain reference for the future artificial assignment of specific colors of the Vienna test paper, such as pH meter readings. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0015] Figure 1 This is a schematic diagram of the architecture of a Vienna stability test system provided in an embodiment of the present application;

[0016] Figure 2 This is a schematic structural diagram of a stability determination device provided in an embodiment of the present application;

[0017] Figure 3 Schematic diagram of a stability tester and a camera device provided in an embodiment of the present application;

[0018] Figure 4 This is a schematic diagram of the internal layout of a stability tester provided in an embodiment of the present application;

[0019] Figure 5is a top view of a gas sensor provided in an embodiment of the present application;

[0020] Figure 6 yes Figure 5 A side view of the gas sensor in FIG.

[0021] Figure 7 This is a partial schematic diagram of the network structure of a YOLOv5s image recognition model provided in an embodiment of the present application;

[0022] Figure 8 1 is a flow chart of a method for determining the stability of a Vienna stability test system provided in an embodiment of the present application.

[0023] Reference numerals:

[0024] 1. Stability determination device; 11. Display screen; 12. Equipment buttons; 13. Operation platform; 14. Controller;

[0025] 2. Stability test device; 21. Stability tester; 211. Upper cover; 212. Constant temperature chamber; 213. Peep window; 214. Control console; 22. First test beaker; 23. Beaker stand; 231. Handle;

[0026] 3. Camera device; 31. Camera; 32. Camera bracket;

[0027] 4. Gas detection device; 41. Second test beaker; 42. Gas sensor; 421. Heating plate; 422. Metal oxide semiconductor layer; 423. Thermally conductive and electrically insulating layer. DETAILED DESCRIPTION

[0028] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0029] A Vienna stability test system and a stability determination method according to an embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0030] The present application embodiment provides a Vienna qualitative test system, such as Figure 1 As shown, the Vienna stability test system includes a stability test device 2, a camera device 3, a gas detection device 4 and a stability determination device 1;

[0031] Combine Figure 1 、 Figure 2 、 Figure 3 and Figure 4 As shown, specifically, the stability test device 2 includes a stability tester 21, a first test beaker 22 and a Vienna test paper (not shown); the gas detection device 4 includes a second test beaker 41 and a gas sensor 42; the stability tester 21 is provided with a peep window 213, the first test beaker 22 and the second test beaker 41 are both arranged in the stability tester 21, the Vienna test paper is arranged in the first test beaker 22, and the gas sensor 42 is arranged in the second test beaker 41, and the first test beaker 22 is positioned opposite the peep window 213; the first test beaker 22 is used to place a first sample, and the second test beaker 41 is used to place a second sample of the same type and quality as the first sample; the stability test device 2 is used to perform stability tests on the first sample and the second sample; the gas detection device 4 is used to detect the gas concentration generated by the second sample during the synchronous stability test of the first sample and the second sample, and send the gas concentration to the stability judgment device 1;

[0032] The camera device 3 is located outside the stability tester 21 and facing the peep window 213. The camera device 3 is used to capture multiple test paper images of the Vienna test paper in the first test beaker 22 during the synchronous stability test of the first sample and the second sample, and send the multiple test paper images to the stability determination device 1;

[0033] The stability determination device 1 is used to receive multiple test paper images and input the multiple test paper images into a trained image recognition model, identify the color of each test paper image through the image recognition model, and output a determination result when the color of the test paper image is identified as the endpoint color. It is also used to quantitatively determine the reaction degree of the second sample when the color of the Vienna test paper changes to the endpoint color based on the determination result and the gas concentration.

[0034] According to the technical solution provided in the embodiments of the present application, not only can the endpoint color of the Vienna test paper be automatically identified, thereby replacing the long-standing method of using the human eye to determine the endpoint color and improving the accuracy of the stability test results, but also by monitoring the gas concentration generated by the sample during the sample test, the reaction depth reached by the sample when the color of the Vienna test paper changes to the endpoint color can be more intuitively obtained, thereby quantifying the sample reaction process and providing a certain reference for the future artificial assignment of specific colors of the Vienna test paper, such as similar to pH meter readings.

[0035] Alternatively, as Figure 2As shown, the stability determination device 1 includes a display screen 11, device buttons 12, an operating platform 13, and a controller 14. Controller 14 includes a PLC module and an industrial computer. The operating platform 13 is used to place a keyboard and mouse, and the device buttons 12 are used to operate the stability determination device 1. The power cord of the industrial computer is connected to a power outlet, and the PLC and the industrial computer are connected via a serial port for data transmission and communication. The power module of the device buttons 12 and the display screen 11 is connected to the power supply of the PLC module to power the PLC module. The I / O module of the PLC module is connected to the device buttons 12 and the display screen 11 respectively for exchanging external information.

[0036] Alternatively, as Figure 3 and Figure 4 As shown, the stability tester 21 includes an upper cover 211, a constant temperature box 212, a peep window 213, a console 214, a beaker rack 23, a first test beaker 22 and Vienna test paper (not shown), and a handle 231 is provided on the beaker rack 23.

[0037] The upper cover 211 is located above the constant temperature box 212. The upper cover 211 is used to place the test beaker into the beaker rack 23. When the upper cover 211 is opened, the test beaker can be placed into the beaker rack 23. When the upper cover 211 is closed, a stability test can be performed on the sample.

[0038] The constant temperature box 212 is located above the control console 214. The constant temperature box 212 is used to heat the sample. The control console 214 is used to control the temperature of the constant temperature box 212. When the temperature of the constant temperature box 212 reaches a preset temperature, a stability test is performed on the sample.

[0039] The shell of the constant temperature box 212 is provided with a peep window 213, which is used for the external camera device 3 to capture the color change of the Vienna test paper in the first test beaker 22 during the stability test of the sample;

[0040] The beaker rack 23 is located in the constant temperature box 212, the first test beaker 22 is located in the beaker rack 23 and facing the peep window 213, the Vienna test paper is located in the first test beaker 22, and the beaker rack 23 is used to place the test beaker to perform a stability test on the sample in the test beaker.

[0041] Alternatively, as Figure 3 As shown, the camera device 3 includes a camera 31 and a camera bracket 32. The camera 31 is fixed to the top of the camera bracket 32 ​​and is located outside the stability tester 21 and directly opposite the peep window 213. The camera 31 is used to capture multiple test paper images of the Vienna test paper in the first test beaker 22 in real time during the synchronous stability test of the first sample and the second sample, and transmit the multiple test paper images to the stability determination device 1. The camera 31 can be an intelligent high-definition camera.

[0042] In some embodiments, the image recognition model is a YOLOv5s image recognition model;

[0043] like Figure 7 As shown in Figure 1, the YOLOv5s image recognition model includes a focusing module, a three-convolution cross-stage local bottleneck module, a graph compression module, and a spatial pyramid pooling module.

[0044] The focusing module is used to slice, splice and convolve the test strip image to obtain a double-downsampled feature map without information loss;

[0045] The three-convolution cross-stage local bottleneck module, namely the C3 module, is used to extract features from the doubled downsampled feature map and output the first feature map;

[0046] A graphics compression module, namely a Ghostconv module, is used to perform convolution and linear mapping operations on the first feature map and output a second feature map;

[0047] The spatial pyramid pooling (SPP) module is used to perform a pooling operation on the second feature map.

[0048] Specifically, the Focus module performs slicing, concat (splicing) and convolution operations on the test paper image in sequence to obtain a double-downsampled feature map without information loss. The structure of the C3 module deletes one Conv in each bottleneck structure, first dividing the feature map of the base layer into two parts, and then merging them through a cross-stage hierarchy. The network structure of the C3 module can reduce the probability of information duplication. The newly introduced Ghostconv module replaces the traditional Conv module. It is used for information features between convolution channels, and makes full use of the relationship between feature extraction and feature mapping redundancy. It effectively reduces the number and time of parameters, floating-point calculations of the image recognition model, while ensuring detection performance and achieving lightweight calculations. The SPP module chooses to use one feature extraction for calculation, accepts images of different sizes, and finally outputs.

[0049] This embodiment specifically adopts the YOLOv5s image recognition model. By adding the Ghostconv module, the network structure of the YOLOv5s image recognition model is optimized, which effectively reduces the number and time of model parameters and floating-point calculations, while also ensuring detection performance and achieving lightweight computing.

[0050] In some embodiments, from the start to the end of the stability test of the first sample, the theoretical color change order of the Vienna test paper is blue, blue-purple, purple, purple-rose, rose, and red, wherein red is the endpoint color;

[0051] The stability judgment device 1 is used to receive multiple test paper images and input the multiple test paper images into a trained image recognition model, identify the color of each test paper image through the image recognition model, and output the corresponding judgment result when the color of the test paper image is identified as blue, blue-purple, purple, purple-rose, rose or red.

[0052] The image recognition module of this embodiment can identify each stage of the color change of the Vienna test paper during the stability test of the sample, that is, during the stability test of the sample, when the color of the test paper image is blue, the image recognition model outputs a blue discrimination result; when the color of the test paper image is blue-purple, the image recognition model outputs a blue-purple discrimination result; when the color of the test paper image is purple, the image recognition model outputs a purple discrimination result; when the color of the test paper image is purple-rose, the image recognition model outputs a purple-rose discrimination result; when the color of the test paper image is rose, the image recognition model outputs a rose discrimination result; when the color of the test paper image is red, the image recognition model outputs a red discrimination result.

[0053] In this embodiment, the image recognition model compares multiple test strip images in real time, accurately identifying the test phase corresponding to each color. When the endpoint color is recognized, the camera 3 is controlled to stop recording and a prompt message is output to remind the operator that the test has ended and the stability tester 21 can be shut down.

[0054] In some embodiments, the training process of the image recognition model includes:

[0055] Obtain a dataset of Vienna test strips; wherein the dataset includes a blue dataset, a blue-purple dataset, a purple dataset, a purple-rose dataset, a rose dataset, and a red dataset;

[0056] Divide the data set into a training set and a test set according to a preset ratio, wherein the ratio of the training set is greater than the ratio of the test set; wherein the training set includes a blue training set, a blue-purple training set, a purple training set, a purple-rose training set, a rose training set, and a red training set, and the test set includes a blue test set, a blue-purple test set, a purple test set, a purple-rose test set, a rose test set, and a red test set;

[0057] Inputting the training set into the neural network model, training the neural network model until the recognition result of the neural network model reaches the predetermined recognition result, thereby completing the training of the neural network model;

[0058] Verify the trained neural network model through the test set;

[0059] If the discrimination results output by the neural network model are the same as the preset discrimination results and the error of the discrimination results is within the preset range, the trained neural network model is used as the image recognition model;

[0060] If the discrimination results output by the neural network model are different from the preset discrimination results, or the error of the discrimination results is not within the preset range, the step of obtaining the data set of the Vienna test paper is re-executed after adjusting the parameters until the discrimination results output by the neural network model are the same as the preset discrimination results and the error of the discrimination results is within the preset range.

[0061] Specifically, 250 images of blue, blue-purple, purple, purple-rose, rose, and red Vienna test strips can be obtained, for a total of 1,500 images of Vienna test strips. Among the 1,500 images of Vienna test strips, the images of each color are divided into training sets and test sets in a ratio of 9:1. The training set is used to iteratively train the YOLOv5s neural network model, and the test set verifies the performance of the trained neural network model and the error of the discrimination result. If the discrimination result and the error both meet the preset requirements, the trained neural network model is used as the image recognition model. If the discrimination result and the error both meet the preset requirements and do not meet the requirements, the parameters are adjusted and retrained until the loss function is almost stable, the YOLOv5s neural network model is optimized, and the discrimination results output by the neural network model are the same as the preset discrimination results and the error of the discrimination results are within the preset range.

[0062] In some embodiments, the stability judgment device 1 is also used to determine that an abnormality has occurred in the stability test process and output a prompt message when the stability judgment device 1 does not output a corresponding judgment result for any test paper image, or when the order of multiple identified judgment results is different from the theoretical change order.

[0063] The stability determination device 1 provided in the embodiment of the present application can also determine whether an abnormality occurs during the stability test of the sample. If an abnormality occurs, a prompt message is output to remind the operator that an abnormality occurs during the stability test of the sample.

[0064] In some embodiments, the stability judgment device 1 is used to quantitatively judge the reaction degree of the second sample when the color of the Vienna test paper changes to blue, blue-purple, purple, purple-rose, rose and red according to the judgment results and gas concentration during the synchronous stability test of the first sample and the second sample.

[0065] The stability judgment device 1 provided in the embodiment of the present application can more intuitively obtain the reaction depth reached by the sample when the color of the Vienna test paper changes to different colors by monitoring the gas concentration generated by the sample during the sample test process. That is, by comparing the obtained gas concentration with the different stages of color change of the Vienna test paper in real time, the sample reaction process is quantified, providing a certain reference for artificially assigning specific colors of the Vienna test paper in the future, such as similar to pH meter readings.

[0066] In some embodiments, one side of the Vienna paper is placed against the inner wall and bottom of the first test beaker 22, and the other side of the Vienna paper faces outward, and the other side of the Vienna paper is a textured surface. The first sample in the first test beaker 22 retains a trace amount of moisture before the stability test, wherein the trace amount of moisture is not less than 1% and not more than 1.5% of the mass of the first sample.

[0067] In some embodiments, as Figure 4 As shown, a gas sensor 42 is vertically and securely mounted within a second test beaker 41. The second sample within the second test beaker 41 is dried to remove any moisture prior to the stability test. Both the first test beaker 22 containing the Vienna test paper and the second test beaker 41 containing the gas sensor 42 are placed within a beaker rack 23.

[0068] In some embodiments, as Figure 5 and Figure 6 As shown, the gas sensor 42 includes a heating plate 421, a metal oxide semiconductor layer 422 and a thermally conductive and electrically insulating layer 423;

[0069] One side of the metal oxide semiconductor layer 422 is in contact with the heating plate 421 and the thermally conductive and electrically insulating layer 423 , and the other side is exposed to the gas to be measured.

[0070] The material of the metal oxide semiconductor layer 422 includes at least one of tin oxide, tungsten oxide and zinc oxide; optionally, the material of the metal oxide semiconductor layer 422 may further include a doping catalyst such as palladium or platinum.

[0071] The thickness of the metal oxide semiconductor layer 422 is not less than 50 nanometers and not more than 60 nanometers;

[0072] The resistance of the metal oxide semiconductor layer 422 is inversely proportional to the concentration of the detected gas.

[0073] The gas sensor 42 in this embodiment performs resistance sensing, and the resistance of the metal oxide semiconductor layer 422 (ie, the gas sensing layer) thereof changes inversely proportional to the concentration of the target gas being detected.

[0074] Specifically, gas sensor 42 can be a thin semiconductor gas sensor, used to collect real-time nitrogen oxide gas concentrations generated when the sample is heated. Gas sensor 42 is vertically fixed in second test beaker 41. The second sample in second test beaker 41 is dried to remove moisture prior to the stability test. First test beaker 22 is positioned directly opposite peephole 213, with the inner side of the Vienna paper in close contact with the inner wall and bottom of first test beaker 22, with the other side of the Vienna paper facing outward. The other side of the Vienna paper is a textured surface. Prior to the stability test, the first sample in first test beaker 22 retains a trace of moisture (e.g., 1% to 1.5% of the sample's mass). The working principle of the gas sensor 42 is based on electrochemical reaction. When nitrogen oxide gas passes through the gas sensor 42, the gas molecules undergo redox reaction with the metal oxide surface, causing the voltage and current in the circuit of the gas sensor 42 to change. The voltage and current are then transmitted to the signal processing circuit of the gas sensor 42 for processing. The collected electrical signal is amplified, filtered, compared, and other processing, and finally a digital signal of the nitrogen oxide gas concentration is output to the stability judgment device 1.

[0075] The display screen 11 of the stability determination device 1 displays the NOx gas concentration fraction generated by the decomposition of the sample in real time. By comparing the obtained gas concentration fraction with the color change stage of the Vienna test paper in real time, the sample reaction process can be quantified.

[0076] The following stability test is carried out by taking the sample as mixed nitrate propellant and the Vienna test paper as litmus paper as an example. The steps of the stability test can be referred to the following two embodiments.

[0077] Example 1:

[0078] Turn on the stability tester 21, set the heating temperature to 106.5°C, and start heating;

[0079] After drying the mixed nitrate propellant, six portions of the same mass of mixed nitrate propellant ZY-1 (NC 57.5%, NG+TEGDN 40%, C 22.0%, and other 0.5%) were weighed and placed in a professional beaker. Three portions of the mixed nitrate propellant were placed in a first test beaker 22. Each of the mixed nitrate propellant samples in the first test beaker 22 retained a trace of moisture, which accounted for 1% to 1.5% of the mass of each sample. The first test beaker 22 was equipped with litmus paper. The other three portions of the mixed nitrate propellant were placed in a second test beaker 41. None of the three mixed nitrate propellant samples in the second test beaker 41 retained any moisture. The second test beaker 41 was equipped with a gas sensor 42.

[0080] When the temperature in the constant temperature box 212 of the stability tester 21 reaches and stabilizes at the set temperature value of 106.5° C., the first test beaker 22 and the second test beaker 41 are placed in the beaker rack 23 in the constant temperature box 212 , with the first test beaker 22 facing the peep window 213 .

[0081] The image of the litmus paper during the test of the mixed nitrate propellant is collected in real time by a camera, and the collected image of the litmus paper is transmitted to the stability determination device 1.

[0082] When the stability judging device 1 recognizes that the color of the litmus paper image is the end point red, it means that the color of the litmus paper has changed to red during the test of the mixed nitrate propellant, and a prompt message is output to remind the operator that the test is over and record relevant data.

[0083] The time when the litmus paper reached the end point "red" for the three samples in this embodiment is shown in Table 1.

[0084] Table 1: Time when litmus paper reaches the end point "red"

[0085] Sample 1 Sample 2 Sample 3 Time (h) 60.5 60.5 60.3

[0086] Example 2:

[0087] Turn on the stability tester 21, set the heating temperature to 106.5°C, and start heating;

[0088] After drying the mixed nitrate propellant, six portions of the same mass of mixed nitrate propellant ZY-2 (NC 60%, NG+TEGDN 37.5%, C 22.0%, and other 0.5%) were weighed and placed in a professional beaker. Three of the mixed nitrate propellant samples were placed in a first test beaker 22. Each of the mixed nitrate propellant samples in the first test beaker 22 retained a trace of moisture, which accounted for 1% to 1.5% of the mass of each sample. The first test beaker 22 was equipped with litmus paper. The other three mixed nitrate propellant samples were placed in a second test beaker 41. None of the three mixed nitrate propellant samples in the second test beaker 41 retained any moisture. The second test beaker 41 was equipped with a gas sensor 42.

[0089] When the temperature in the constant temperature box 212 of the stability tester 21 reaches and stabilizes at the set temperature value of 106.5° C., the first test beaker 22 and the second test beaker 41 are placed in the beaker rack 23 in the constant temperature box 212 , with the first test beaker 22 facing the peep window 213 .

[0090] The image of the litmus paper during the test of the mixed nitrate propellant is collected in real time by a camera, and the collected image of the litmus paper is transmitted to the stability determination device 1.

[0091] When the stability judging device 1 recognizes that the color of the litmus paper image is the end point red, it means that the color of the litmus paper has changed to red during the test of the mixed nitrate propellant, and a prompt message is output to remind the operator that the test is over and record relevant data.

[0092] The time taken for the three test papers to reach the end point of "red" in this embodiment is shown in Table 2.

[0093] Table 2: Time when litmus paper reaches the end point "red"

[0094] Sample 1 Sample 2 Sample 3 Time (h) 63.5 63.6 63.5

[0095] Based on the same inventive concept, the embodiment of the present application provides a method for determining the stability of a Vienna stability test system, which is applied to a stability determination device of a Vienna stability test system provided in any of the above embodiments, such as Figure 8 As shown in the figure, the stability determination method of the Vienna stability test system includes:

[0096] S101, during a stability test of a first sample, receiving a plurality of test paper images of Vienna test paper in a first test beaker captured by a camera device;

[0097] S102, inputting multiple test strip images into a trained image recognition model, identifying the color of each test strip image through the image recognition model, and outputting a discrimination result when the color of the test strip image is identified as the endpoint color;

[0098] S103, based on the discrimination result and the gas concentration, quantitatively discriminate the reaction degree of the second sample when the color of the Vienna test paper changes to the end point color.

[0099] According to the technical solution provided in the embodiments of the present application, not only can the endpoint color of the Vienna test paper be automatically identified, thereby replacing the long-standing method of using the human eye to determine the endpoint color and improving the accuracy of the stability test results, but also by monitoring the gas concentration generated by the sample during the sample test, the reaction depth reached by the sample when the color of the Vienna test paper changes to the endpoint color can be more intuitively obtained, thereby quantifying the sample reaction process and providing a certain reference for the future artificial assignment of specific colors of the Vienna test paper, such as similar to pH meter readings.

[0100] In some embodiments, from the start to the end of the stability test of the first sample, the theoretical color change order of the Vienna test paper is blue, blue-purple, purple, purple-rose, rose, and red, wherein red is the endpoint color;

[0101] Multiple test strip images are input into a trained image recognition model. The image recognition model identifies the color of each test strip image. When the color of the test strip image is identified as the endpoint color, the judgment result is output, including:

[0102] Multiple test paper images are input into a trained image recognition model, and the color of each test paper image is identified by the image recognition model. When the color of the test paper image is identified as blue, blue-purple, purple, purple-rose, rose or red, the corresponding discrimination result is output.

[0103] In some embodiments, quantitatively determining the reaction degree of the second sample when the color of the Vienna test paper changes to the endpoint color based on the determination result and the gas concentration includes:

[0104] According to the discrimination result and the gas concentration, the reaction degree of the second sample when the color of the Vienna test paper changes to blue, blue-purple, purple, purple-rose, rose and red is quantitatively discriminated.

[0105] All of the above optional technical solutions can be combined in any way to form optional embodiments of the present application, and will not be described in detail here.

[0106] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0107] Based on the same inventive concept, an embodiment of the present application provides an electronic device. The electronic device of this embodiment includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of each of the aforementioned method embodiments are implemented. Alternatively, when the processor executes the computer program, the functions of each module / unit in each of the aforementioned device embodiments are implemented.

[0108] The electronic device may be a desktop computer, a laptop, a PDA, a cloud server, or other electronic device. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the electronic device may include more or fewer components than shown, or different components.

[0109] The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0110] Memory can be an internal storage unit of an electronic device, such as a hard drive or memory. It can also be an external storage device, such as a plug-in hard drive, a SmartMedia Card (SMC), a Secure Digital (SD) card, or a flash memory card. Memory can also include both internal storage units and external storage devices. Memory is used to store computer programs and other programs and data required by the electronic device.

[0111] Based on the same inventive concept, an embodiment of the present application provides a readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the method described in any of the above embodiments are implemented.

[0112] The readable storage medium provided in the embodiment of the present application has the same inventive concept and the same beneficial effects as the previous embodiments. The contents not shown in detail in the readable storage medium can be referred to the previous embodiments and will not be repeated here.

[0113] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and devices is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and devices as needed, that is, the internal structure of the device can be divided into different functional units or devices to complete all or part of the functions described above. The functional units and devices in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0114] If the integrated device / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium (such as a computer-readable storage medium). Based on this understanding, the present application implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. The computer program may include computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. Computer-readable storage media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0115] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A Vienna stability test system, characterized in that: include: Stability test equipment, camera equipment, gas detection equipment and stability identification equipment; The stability testing device includes a stability tester, a first test beaker, and Vienna paper; the gas detection device includes a second test beaker and a gas sensor; the stability tester is provided with a peep window, the first test beaker and the second test beaker are both arranged in the stability tester, the Vienna paper is arranged in the first test beaker, and the gas sensor is arranged in the second test beaker, with the first test beaker positioned opposite the peep window; the first test beaker is used to place a first sample, and the second test beaker is used to place a second sample of the same type and quality as the first sample; the stability testing device is used to perform a stability test on the first sample and the second sample; the gas detection device is used to detect the gas concentration generated by the second sample during the simultaneous stability test of the first and second samples, and send the gas concentration to the stability determination device; The camera device is located outside the stability tester and facing the peep window. The camera device is used to capture multiple test paper images of the Vienna test paper in the first test beaker during the synchronous stability test of the first sample and the second sample, and send the multiple test paper images to the stability determination device. The stability discrimination device is used to receive a plurality of test paper images and input the plurality of test paper images into a trained image recognition model, and to identify the color of each test paper image through the image recognition model. From the start to the end of the stability test of the first sample, the theoretical color change order of the Vienna test paper is blue, blue-purple, purple, purple-rose, rose, and red, wherein red is the end point color. When the color of the test paper image is identified as blue, blue-purple, purple, purple-rose, rose, or red, the corresponding discrimination result is output. The device is also used to quantitatively determine the reaction degree of the second sample when the color of the Vienna test paper changes to blue, blue-purple, purple, purple-rose, rose, and red based on the discrimination result and the gas concentration. The stability determination device is further configured to: determine that an abnormality has occurred in the stability test process and output a prompt message when the stability determination device fails to output a corresponding determination result for any test paper image, or when the order of the identified multiple determination results is different from the theoretical change order; The stability judging device comprises a display screen for displaying in real time the concentration fraction of NOx gas generated by decomposition of the sample.

2. The system according to claim 1, wherein: The image recognition model is a YOLOv5s image recognition model; The YOLOv5s image recognition model includes a focusing module, a three-convolution cross-stage local bottleneck module, a graph compression module, and a spatial pyramid pooling module; The focusing module is used to perform slicing, splicing and convolution operations on the test paper image to obtain a double down-sampled feature map without information loss; The three-convolution cross-stage local bottleneck module is used to extract features from the double-downsampled feature map and output a first feature map; The graphics compression module is configured to perform convolution and linear mapping operations on the first feature map to output a second feature map; The spatial pyramid pooling module is used to perform a pooling operation on the second feature map.

3. The system according to claim 1, wherein: The stability judgment device is also used to determine that an abnormality has occurred in the stability test process and output a prompt message when the stability judgment device does not output the corresponding judgment result for any of the test paper images, or when the order of the multiple identified judgment results is different from the theoretical change order.

4. The system according to claim 1, wherein: One side of the Vienna paper is in close contact with the inner wall and bottom of the first test beaker, and the other side of the Vienna paper faces outward, and the other side of the Vienna paper is a textured surface. The first sample inside the first test beaker retains a trace of moisture before the stability test, wherein the trace moisture is not less than 1% of the mass of the first sample and not more than 1.5% of the mass of the first sample.

5. The system according to claim 1, wherein: The gas sensor is vertically and fixedly arranged in the second test beaker; the second sample inside the second test beaker is dried before the stability test and does not retain moisture.

6. The system according to claim 1, wherein: The gas sensor comprises a heating plate, a metal oxide semiconductor layer and a heat-conducting and electrically insulating layer; One side of the metal oxide semiconductor layer is in contact with the heating plate and the heat-conducting and electrically insulating layer, and the other side is exposed to the gas to be measured.

7. The system according to claim 6, characterized in that The material of the metal oxide semiconductor layer includes at least one of tin oxide, tungsten oxide and zinc oxide; The thickness of the metal oxide semiconductor layer is not less than 50 nanometers and not more than 60 nanometers; The resistance value of the metal oxide semiconductor layer is inversely proportional to the concentration of the detected gas.

8. A method for determining the stability of a Vienna stability test system, characterized in that: The stability determination device applied to the Vienna stability test system according to any one of claims 1 to 7, wherein the method comprises: During a stability test of a first sample, receiving a plurality of test paper images of Vienna test paper in a first test beaker captured by a camera device; Inputting the plurality of test paper images into a trained image recognition model, identifying the color of each test paper image through the image recognition model, and outputting a discrimination result when the color of the test paper image is identified as the endpoint color; The reaction degree of the second sample when the color of the Vienna test paper changes to the endpoint color is quantitatively determined according to the discrimination result and the gas concentration.

Images