Sample liquid-solid phase change detection device and method

Abstract

The invention belongs to the technical field of liquid-solid phase change detection, and discloses a sample liquid-solid phase change detection device and method.The method comprises the steps that a measuring cavity is filled with a fluid sample to be detected, the detection device is started, the sample is cooled to a preset fluid crystallization point and then cooled, during the period, a laser sensing unit obtains the light transmittance, a camera module obtains a morphological image, and the liquid-solid phase change detection result is obtained. The temperature sensor and the pressure sensor acquire temperature and pressure data respectively, image features are extracted, light transmissivity, temperature and pressure data are subjected to normalization processing and converted into a one-dimensional matrix, the one-dimensional matrix serves as input of a phase change detection model for feature detection, the phase change detection model constructed through a BP neural network is used for processing measurement data, and phase change morphological features are acquired. According to the technical scheme, the integrated liquid-solid phase change detection device and method are designed, and the accuracy and reliability of phase change process detection can be improved.

Description

Technical Field

[0001] The invention belongs to the technical field of liquid-solid phase change detection, and in particular relates to a sample liquid-solid phase change detection device and method. Background Art

[0002] As one of the basic processes of material state transformation, the transformation mechanism of liquid-solid phase transition (process morphology, characteristic parameters, phase transition point) has extremely important research value for thermodynamics, kinetics, materials science, renewable energy utilization, etc. At present, the detection methods of liquid-solid phase transition process mainly include differential scanning calorimetry, PT phase diagram method, visual bench method, X-ray diffraction method, infrared spectroscopy, etc.

[0003] Although the existing liquid-solid phase change process detection technology has been applied and promoted to a certain extent in different scientific research and engineering scenarios, it is limited by the defects or shortcomings of the detection method itself. The use of a single detection technology can often only identify a specific process parameter in the phase change process, and cannot fully reflect the complex liquid-solid phase change process, affecting the objective evaluation of the phase change behavior and mechanism. Summary of the invention

[0004] The object of the present invention is to provide a sample liquid-solid phase change detection device and method to solve the problems existing in the above-mentioned prior art.

[0005] To achieve the above object, the present invention provides a sample liquid-solid phase change detection device, comprising:

[0006] A measuring cavity, wherein the measuring cavity is arranged inside the detection box, and a plurality of light sources are installed on the top of the measuring cavity; a liquid inlet, a pressurization port and a plurality of sensor installation ports connected to the measuring cavity are provided on the top of the detection box, a liquid discharge port connected to the measuring cavity is provided on the bottom of the detection box, and corresponding observation windows are provided on the front side wall of the measuring cavity and the front side wall of the detection box;

[0007] A laser sensor unit, comprising a laser sensor transmitting module and a laser sensor receiving module, wherein the laser sensor transmitting module and the laser sensor receiving module are symmetrically arranged on the left and right sides of the detection box;

[0008] A sensor group, including a temperature sensor and a pressure sensor, wherein the temperature sensor and the pressure sensor are installed in corresponding sensor installation ports;

[0009] A camera module, the camera module is arranged at one side of the detection box and corresponds to the position of the front side wall of the detection box;

[0010] The control unit includes a main controller and a signal excitation module, a timing module, a data acquisition module and a temperature control module electrically connected to the main controller; the camera module, the laser sensor unit and the sensor group are all electrically connected to the data acquisition module, the signal excitation module is also electrically connected to the laser sensor emission module, and the detection box is electrically connected to the temperature control module.

[0011] Optionally, a constant temperature medium layer and a heat preservation layer are sequentially arranged between the outer wall of the measurement cavity and the inner wall of the detection box.

[0012] Optionally, it is characterized in that a constant temperature medium inlet is opened on the outer wall of the detection box, and the constant temperature medium inlet passes through the insulation layer and is connected with the constant temperature medium layer.

[0013] Optionally, each laser emitter in the laser sensor transmitting module is arranged in one-to-one correspondence with each laser receiver in the laser sensor receiving module, each laser emitter is connected to the signal excitation module, and each laser receiver is connected to the data acquisition module.

[0014] A sample liquid-solid phase change detection method, applied to a sample liquid-solid phase change detection device, comprising:

[0015] Step 1: Filling the measurement cavity with a sample to be tested, wherein the sample to be tested is in a fluid state;

[0016] Step 2: Turn on the sample liquid-solid phase change detection device, measure the phase change state of the sample to be tested in combination with a preset temperature, and record the measurement data, the measurement data including light transmittance data, morphological image data, phase change temperature data and phase change pressure data;

[0017] Step three: input the measurement data into a phase change detection model integrated in the main controller to perform feature detection to obtain phase change morphological feature data, wherein the phase change detection model is constructed based on a BP neural network.

[0018] Optionally, the process of acquiring the measurement data specifically includes:

[0019] The temperature control module is controlled to cool the sample to be tested until the sample to be tested is cooled to a preset fluid crystallization point threshold, and then the temperature is lowered; in the process of cooling the sample to be tested, the signal excitation module is used to excite the laser sensor unit to obtain light transmittance data; the camera module is used to obtain the morphological image data of the sample to be tested in the measuring cavity, the temperature sensor is used to obtain the phase change temperature data, and the pressure sensor is used to obtain the phase change pressure data.

[0020] Optionally, before inputting the measurement data into the phase change detection model, the method further includes:

[0021] Performing feature extraction on the morphological image data to obtain image feature data;

[0022] The light transmittance data, phase change temperature data and phase change pressure data are normalized based on the time series to obtain normalized data, the normalized data and the image feature data are converted into one-dimensional matrix data to obtain preprocessed measurement data, and the preprocessed measurement data is used as the input of the phase change detection model for feature detection.

[0023] Optionally, the training process of the phase change detection model specifically includes:

[0024] Acquiring training data, wherein the training data includes measurement training data and corresponding phase change morphology characteristic data;

[0025] An initial phase change detection model is constructed, the training data is input into the initial phase change detection model, the light transmittance data, phase change temperature data and phase change pressure data are used to quantitatively analyze the characteristics of the morphological image data to obtain initial phase change morphological feature data, and training is performed with the goal of minimizing the loss between the initial phase change morphological feature data and the phase change morphological feature data corresponding to the measured training data to obtain a trained phase change detection model.

[0026] The technical effects of the present invention are:

[0027] The present invention is based on the theory of multi-source information fusion, and adopts UG and CFD simulation technology to integrate the visualization bench method (microscope observation method and laser transmission method), temperature detection method, pressure detection method, etc., and uses them together for liquid-solid transformation process detection (including morphology, light transmittance, phase change temperature and pressure). The characteristics of different detection methods are used to carry out multi-dimensional angle cross-measurement, which can avoid the defects and shortcomings of single detection methods. In addition, for the information of different magnitudes, forms and units such as images, light transmittance, phase change temperature, phase change pressure, etc. obtained by detection, convolutional neural networks and normalization algorithms can be used to convert them to the same magnitude and interval through information classification, extraction of characteristic variables, dimensionless standardization, etc., and then use the BP neural network algorithm to obtain the measurement model of the new liquid-solid phase change detection device. The present invention combines multi-dimensional detection with neural network algorithms to design a set of integrated liquid-solid phase change detection devices and methods, which can improve the accuracy and reliability of phase change process detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0029] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0030] Figure 1 Schematic diagram of the structure of a novel liquid-solid phase change detection device in an embodiment of the present invention;

[0031] Figure 2 It is an analytical diagram of the preprocessing and fusion process of multi-source information in an embodiment of the present invention;

[0032] Figure 3 This is a flow chart of extracting morphological image feature vectors based on a convolutional neural network in an embodiment of the present invention;

[0033] Figure 4 Schematic diagram of the structure of the phase change morphological feature measurement model based on BP neural network in an embodiment of the present invention. DETAILED DESCRIPTION

[0034] Various exemplary embodiments of the present invention will now be described in detail. This detailed description should not be considered as limiting the present invention, but should be understood as a more detailed description of certain aspects, features, and embodiments of the present invention.

[0035] It should be understood that the terms described in the present invention are only for describing special embodiments and are not intended to limit the present invention. In addition, for the numerical range in the present invention, it should be understood that each intermediate value between the upper and lower limits of the scope is also specifically disclosed. Each smaller range between the intermediate value in any stated value or stated range and any other stated value or intermediate value in the described range is also included in the present invention. The upper and lower limits of these smaller ranges can be independently included or excluded in the scope.

[0036] Unless otherwise indicated, all technical and scientific terms used herein have the same meanings as those of ordinary skill in the art generally understood by the present invention. Although the present invention describes only preferred methods, any method similar or equivalent to that described herein may also be used in the implementation or testing of the present invention. All documents mentioned in this specification are incorporated by reference to disclose and describe the methods related to the documents. In the event of a conflict with any incorporated document, the content of this specification shall prevail.

[0037] It will be apparent to those skilled in the art that various modifications and variations may be made to the specific embodiments of the present invention description without departing from the scope or spirit of the present invention. Other embodiments derived from the present invention description will be apparent to those skilled in the art. The present application description and examples are exemplary only.

[0038] The words “include,” “including,” “have,” “contain,” etc. used in this article are open-ended terms, meaning including but not limited to.

[0039] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0040] Embodiment 1

[0041] like Figure 1 - Figure 4 As shown, this embodiment provides a sample liquid-solid phase change detection device, including:

[0042] A measuring cavity, wherein the measuring cavity is arranged inside the detection box, and a plurality of light sources are installed on the top of the measuring cavity; a liquid inlet, a pressurization port and a plurality of sensor installation ports connected to the measuring cavity are provided on the top of the detection box, a liquid discharge port connected to the measuring cavity is provided on the bottom of the detection box, and corresponding observation windows are provided on the front side wall of the measuring cavity and the front side wall of the detection box;

[0043] A laser sensor unit, comprising a laser sensor transmitting module and a laser sensor receiving module, wherein the laser sensor transmitting module and the laser sensor receiving module are symmetrically arranged on the left and right sides of the detection box;

[0044] A sensor group, including a temperature sensor and a pressure sensor, wherein the temperature sensor and the pressure sensor are installed in corresponding sensor installation ports;

[0045] A camera module, the camera module is arranged at one side of the detection box and corresponds to the position of the front side wall of the detection box;

[0046] The control unit includes a main controller and a signal excitation module, a timing module, a data acquisition module and a temperature control module electrically connected to the main controller; the camera module, the laser sensor unit and the sensor group are all electrically connected to the data acquisition module, the signal excitation module is also electrically connected to the laser sensor emission module, and the detection box is electrically connected to the temperature control module.

[0047] A sample liquid-solid phase change detection method, applied to a sample liquid-solid phase change detection device, comprising:

[0048] Step 1: Filling the measurement cavity with a sample to be tested, wherein the sample to be tested is in a fluid state;

[0049] Step 2: Turn on the sample liquid-solid phase change detection device, measure the phase change state of the sample to be tested in combination with a preset temperature, and record the measurement data, the measurement data including light transmittance data, morphological image data, phase change temperature data and phase change pressure data;

[0050] Step three: input the measurement data into a phase change detection model integrated in the main controller to perform feature detection to obtain phase change morphological feature data, wherein the phase change detection model is constructed based on a BP neural network.

[0051] This embodiment is based on the theory of multi-source information fusion, and adopts UG and CFD simulation technology to integrate the visualization bench method (microscope observation method and laser transmission method), temperature detection method, pressure detection method, etc., and uses them together for liquid-solid transformation process detection (including morphology, light transmittance, phase change temperature and pressure). The characteristics of different detection methods are used to carry out multi-dimensional angle cross-measurement, which can avoid the defects and shortcomings of single detection methods. In addition, for the information of different magnitudes, forms and units such as images, light transmittance, phase change temperature, phase change pressure, etc. obtained by detection, convolutional neural networks and normalization algorithms can be used to convert them to the same magnitude and interval through information classification, extraction of characteristic variables, dimensionless standardization, etc., and then use the BP neural network algorithm to obtain the measurement model of the new liquid-solid phase change detection device. The present invention combines multi-dimensional detection with neural network algorithms to design a set of integrated liquid-solid phase change detection devices and methods, which can improve the accuracy and reliability of phase change process detection.

[0052] Limited by the inherent defects or deficiencies of the measurement method, when a single detection technology is used for liquid-solid phase change process detection, it is impossible to conduct a comprehensive and accurate scientific evaluation of the phase change behavior and internal mechanism. In view of this, the present embodiment aims to make full use of the respective advantages of the visualization bench method (microscope observation method, laser transmission method), pressure detection method, and temperature detection method, and simultaneously use them for the liquid-solid phase change process detection of the same material system. Different methods can cross-complement and mutually verify, thereby providing more comprehensive liquid-solid phase change information. On this basis, the BP neural network algorithm can be used to integrate the optical perspective, phase change temperature, phase change pressure and phase change morphological characteristics to construct a measurement model for a new liquid-solid phase change detection device. Further, it can provide strong support for a comprehensive understanding of the liquid-solid transformation mechanism and behavioral characteristics.

[0053] This embodiment makes full use of the visualization bench method (microscope observation method and laser transmission method), phase change pressure detection, phase change temperature detection and other methods for the detection of the liquid-solid transformation process of the same material system. Specifically, the microscope observation method can provide clearly visible material morphological characteristics, and the laser transmission method, pressure detection method, and thermocouple temperature measurement method can provide accurate phase change process parameters and boundary adjustment. On this basis, by taking advantage of the neural network algorithm, the morphological characteristics of the material are integrated with the laser transmittance, phase change temperature, phase change pressure, etc. to construct an accurate and reliable liquid-solid phase change measurement model.

[0054] This embodiment is based on the theory of multi-source information fusion, and uses microscope observation, laser transmission, pressure detection, and temperature detection methods, and is used for feature detection of the liquid-solid phase change process at the same time, so as to obtain relatively more information about the phase change process and improve the accuracy and reliability of the measurement results. In terms of device development, UG mapping technology is used to construct the basic structure of the liquid-solid phase change measurement cavity body, sensor installation position, and visual observation window, and CFD fluid simulation technology is used to further optimize the measurement device structure and sensor parameters to ensure the compatibility and stability between the measurement modules.

[0055] During the measurement process, a multi-channel signal source is used to simultaneously stimulate the laser sensor, temperature sensor, pressure sensor, electron microscope, etc., and the measured light transmittance, phase change temperature, phase change pressure, phase change morphological image and other information are collected in real time by the same acquisition module to ensure the synchronization and consistency of all measurement results. For the measured results, the morphological image of the liquid-solid phase change is first converted into a one-dimensional array through a convolutional neural network as the phase change morphological feature data, and the feature data is extracted to perform normalization and morphological information classification; the transmittance, phase change temperature, and phase change pressure are dimensionlessly standardized through a normalization algorithm. On this basis, the BP neural network algorithm is used, with light transmittance, phase change temperature, and phase change pressure as input variables and phase change morphological feature data as output variables, to establish a mathematical model between the phase change morphological characteristics and process parameters such as phase change temperature, phase change pressure, and light transmittance.

[0056] This embodiment provides a liquid-solid phase change process detection method based on multi-source information fusion, which can improve the reliability and accuracy of the measurement results and facilitate a more comprehensive scientific evaluation of the behavioral characteristics and internal mechanisms of the phase change process.

[0057] In this embodiment, the newly manufactured liquid-solid phase change detection device integrates the visualization platform method (microscope observation method and laser transmission method), pressure detection method, and temperature detection method to obtain more comprehensive liquid-solid transformation process information. At the same time, all measurement results are preprocessed using convolutional neural networks and normalization algorithms, and then a measurement model of the new liquid-solid phase change detection device is constructed using a BP neural network.

[0058] Specific technical solution: First, keep the substance to be tested in a fluid state, and use negative pressure technology to fill the entire measurement cavity with the fluid to be tested. At the beginning of the measurement, the fluid to be tested is cooled by an external temperature control device to induce the fluid to be tested to transform from liquid to solid. At the same time, the laser sensor, electron microscope, temperature sensor, and pressure sensor are triggered by the PC control unit module to start working synchronously at the same time frequency, and the signal acquisition unit synchronously collects various parameter information obtained by the detection. Among them, the electron microscope probe is used to capture the morphological changes of the fluid to be tested during the transformation from liquid to solid, that is, microscopic changes such as molecular aggregation, arrangement, and crystallization; the laser sensor (transmitter and receiver) is used to detect the change in light transmittance during the transformation of the material morphology, which is used to provide a quantitative reference for the visualized morphological change process; the temperature and pressure sensors installed on the measurement cavity are used to detect the slight changes in temperature and pressure during the transformation of the material from liquid to solid, which is used to analyze the behavioral characteristics and internal mechanism of the liquid-solid phase change of the material. At the end of the measurement, the shooting picture and the measurement results of each sensor are first extracted, and the information is classified and preprocessed using a convolutional neural network and dimensionless normalization. Furthermore, the BP neural network algorithm is used to construct a mathematical model between the morphological characteristics and the light transmittance, phase change temperature, and phase change pressure, which is used to comprehensively and accurately analyze the liquid-solid phase change process. In this way, the liquid-solid phase change process detection based on multi-source information fusion can be completed.

[0059] Liquid-solid phase change detection chamber module: In this embodiment, the liquid-solid phase change detection chamber is designed as a cube as a whole, and the finish of the inner wall of the chamber should reach 0.8μm or more to ensure the sealing of each module of the measurement chamber. A boss is designed at the top of the measurement chamber to measure the liquid inlet of the chamber and the increase of the test pressure. The mounting holes of the temperature and pressure sensors are located on both sides of the boss and assembled with NPT thread structure. On the left and right end faces of the measurement chamber, 13 completely symmetrical array-type reserved holes are designed for installing the laser sensor transmitting probe and receiving probe respectively. On the front of the measurement chamber, an observation window made of sapphire glass is designed for installing an electron microscope probe. At the top of the inner part of the measurement chamber, a low-heat multi-point light source is designed to provide bright light for the electron microscope probe. A drain port is designed at the bottom of the measurement chamber to discharge the waste liquid after the measurement chamber experiment; four height-adjustable support feet are also installed at the bottom to adjust the height and horizontal position of the measurement chamber. In addition, the outer wall of the measuring cavity is designed with a temperature control layer to control the temperature of the fluid to be measured, and its inlet and outlet are designed at the diagonal position of the measuring cavity. At the same time, an insulation layer is designed on the outside of the temperature control layer, which is tightly wrapped with multiple layers of insulation cotton to minimize the heat exchange between the measuring cavity and the outside world.

[0060] Multi-sensor detection module: In this embodiment, the multi-sensor detection module includes a laser sensor, an electron microscope probe, a temperature sensor, and a pressure sensor. Among them, the laser sensor includes a transmitting probe and a receiving probe (a total of 13 pairs), which are symmetrically installed on the left and right end faces of the measurement cavity and are evenly distributed in an array shape. The laser is emitted from the transmitter to the receiver. As the substance to be measured changes from the liquid phase to the solid phase, the transmittance of the laser changes accordingly. The phase change process can be quantitatively analyzed based on the light transmittance. During the liquid-solid phase change process, the electron microscope probe is used to observe the aggregation, crystallization and arrangement of the molecules of the substance to be measured, and to capture the image information of the phase change morphological characteristics in real time. In addition, the temperature measurement during the phase change process uses a thermocouple thermometer with high sensitivity and good stability to synchronously detect the temperature variables during the liquid-solid phase change process, and the pressure measurement uses a capacitive pressure sensor with high sensitivity to synchronously detect the temperature variables during the liquid-solid phase change process. The measurement results of light transmittance, phase change temperature, phase change pressure and morphological characteristics are used together for the construction of a liquid-solid phase change measurement model using a BP neural network algorithm after data classification and preprocessing.

[0061] Signal control and acquisition module: This module includes a multi-channel signal excitation unit, a high-precision electronic timer, a multi-channel signal acquisition unit, and a PC centralized control unit. In this embodiment, the multi-channel signal excitation unit provides the required working power to the temperature sensor, pressure sensor, laser sensor, and electron microscope probe, triggering them to start working at the same time; the high-precision electronic timer provides a unified time reference for reading all measurement signals, providing a basis for the fusion of multiple signals. The multi-channel signal acquisition unit is mainly used to record the measured data at high frequency and transmit it to the PC unit in real time for storage. In addition, the PC unit realizes real-time communication and centralized control with different measuring devices through the single-chip unit.

[0062] Processing and fusion of measurement data:

[0063] In this embodiment, in order to achieve consistency in units, magnitudes and intervals of different measurement results, all measurement results are unified based on the real-time sampling time. At the same time, the image information of the liquid-solid phase change is converted into a one-dimensional array using a convolutional neural network, and the transmittance, temperature and pressure are dimensionlessly preprocessed using a normalization algorithm, and they are converted to the same interval and magnitude, and the morphological information is classified in combination with the morphological feature data. On this basis, the BP neural network algorithm is used to cross-fuse all feature parameters, and a liquid-solid phase change measurement model based on morphological features, transmittance, phase change temperature and phase change pressure is further established.

[0064] Working principle of the new liquid-solid phase change detection device: In this embodiment, first ensure that the substance to be tested is in a liquid flowable state, and fill the entire measuring cavity with the fluid to be tested through vacuum negative pressure technology. Before the measurement begins, ensure that the temperature in the measuring cavity is more than 10°C higher than the crystallization point of the fluid to be tested, and the background pressure of the measuring cavity is maintained at 0.1MPa. Use the level calibrator to adjust the measuring cavity to a horizontal position. At the beginning of the measurement, the PC unit excites the temperature control unit, electronic timer, multi-channel excitation source, sensor unit, signal acquisition unit, etc. to start working synchronously.

[0065] Among them, the internal temperature of the measurement cavity is regulated by the refrigeration cycle fluid to induce the fluid to be tested to cool down until the phase change process is completed. When approaching the crystallization point, the cooling rate must be strictly controlled to ensure that the phase change process is accurately detected. The temperature and pressure changes of the substance to be tested are synchronously detected by the temperature sensor and the pressure sensor, especially to accurately capture the changes in temperature and pressure in the measurement cavity during the liquid-solid transformation. At the same time, PID technology is used to achieve linkage with the temperature control unit to adjust the output power of the temperature control unit. The electron microscope probe is used to detect the changes in the aggregation, arrangement, and crystallization state of the molecules of the substance to be tested in real time, and the array laser sensor is used to synchronously detect the changes in transmittance during the liquid-solid transformation process. The morphological characteristics of the phase change are analyzed based on characteristic variables such as phase change temperature, phase change pressure, and light transmittance.

[0066] During the detection process, the phase change temperature, phase change pressure, light transmittance, morphological image and other detection information are synchronously stored in the PC unit with the same time reference through the data acquisition unit. Then, through convolutional neural network, normalization algorithm, BP neural network and other technical means, a measurement model of the new liquid-solid phase change detection device can be constructed.

[0067] After the measurement is completed, the temperature control unit slowly adjusts the temperature of the substance to be measured to above the crystallization point, and uses the sensor unit to synchronously detect characteristic variables such as temperature, pressure, light transmittance, and morphology in the measurement cavity, so as to realize the reverse process detection and analysis of the liquid-solid phase change. In this embodiment, the liquid inlet at the top of the measurement cavity is designed to serve as a booster port for the background pressure of the fluid to be measured. By increasing the background pressure of the test through an external booster device and repeating the above measurement process, the liquid-solid phase change process under high pressure conditions can be tested and studied.

[0068] Figure 1 This is a schematic diagram of the structure of a new liquid-solid phase change detection device. It mainly detects characteristic parameters such as morphology, transmittance, phase change temperature, and phase change pressure during the liquid-solid transformation process to obtain quantitative phase change process information of the substance to be tested, and supports the analysis and research of phase change behavior characteristics and internal mechanisms. The device mainly includes unit modules such as experimental measurement cavity, temperature and pressure sensors, laser sensors, and electron microscope probes. Example of structural features of the detection device:

[0069] In this embodiment, the material of the liquid-solid phase change measurement cavity is food-grade stainless steel 316L, and the overall design is a cubic structure, and the internal single-side length is designed to be 93.0mm±0.2mm; the top boss is designed as a hollow cylinder, and its height is designed to be 45.0mm±0.2mm, and the inner diameter of the cylinder is designed to be 8.0mm±0.1mm; the single-side wall thickness of the measuring cavity and the boss is designed to be 3.5mm±0.1mm, and the upper limit of the pressure that can be tolerated is 100MPa. The temperature control medium circulation layer is evenly wrapped on the outer wall of the measuring cavity, and its thickness is ≥20.0mm±0.2mm. The inlet and outlet of the temperature control medium are designed as circular pipes, and their inner diameter is 25.0mm±0.2mm, which are located at the upper left corner and lower right corner of the measuring cavity respectively. The observation window on the front of the measuring cavity is designed to be circular, with a radius designed to be 40.0mm±0.1mm, and is made of high-pressure resistant sapphire glass. In addition, 13 array-type symmetrical holes are designed on the left and right end faces of the measuring cavity for installing laser sensor probes, and the inner diameter of the holes is designed to be 9.0mm±0.1mm. On both sides of the top boss of the measuring cavity, there is a hole with an inner diameter of 10.0mm±0.1mm, which is used to install the temperature sensor and pressure sensor respectively. At the bottom center of the measuring cavity, there is a circular drain port with an inner diameter of 30.0mm±0.2mm. Please refer to the attached structural diagram Figure 1 illustrate.

[0070] Before the measurement begins, the vacuum negative pressure technology is used to fill the entire measurement cavity with the substance to be measured in a fluid state to keep the temperature of the fluid to be measured stable. The horizontal calibration instrument and the support feet are used to adjust the absolute horizontal angle of the measurement cavity to ensure the stability of the device during the detection process. At the same time, the laser sensor emission angle and the observation position of the electron microscope probe are accurately adjusted to estimate the crystallization point temperature of the fluid to be measured, and the target temperature of the temperature control module is set to be 3 to 5°C higher than the crystallization point of the fluid to be measured. At the beginning of the measurement, the PC control unit starts the temperature control device, multi-channel signal excitation source, multi-sensor unit, data acquisition unit, electronic timer unit, etc. synchronously through the single-chip microcomputer to start working. During the measurement process, the temperature control module first outputs a constant cooling power. When it is cooled to a target temperature of 3 to 5°C above the crystallization point of the fluid to be measured, the cooling output power of the temperature control module is reduced to slowly reduce the temperature of the measurement cavity. In the sensor module, a high-resolution electron microscope probe captures the image information of the aggregation, arrangement, and crystallization of fluid molecules; based on a uniform array of distributed laser sensors (13 groups), the transmittance of the fluid to be tested is fully detected so as to quantitatively reflect the morphological change process of the fluid; high-sensitivity temperature and pressure sensors are used to accurately detect the temperature and pressure changes during the phase change process. All sensor measurement results must be preprocessed by convolutional neural networks and normalization algorithms before they can be used in the research and construction of liquid-solid phase change measurement models.

[0071] After determining the expected crystallization point temperature of the fluid to be tested, the external temperature control system of the measurement cavity is started, the refrigeration temperature slowly drops, the PC controller sends experimental test instructions to each unit, and the multi-channel signal excitation source triggers the electronic timer, electron microscope probe, laser sensor, temperature sensor, pressure sensor, etc. to start working synchronously, and the liquid-solid transformation process is detected in real time at the same time test frequency to obtain the image, transmittance, phase change temperature, phase change pressure and other characteristic information in the phase change process, which is used for the research and analysis of the mechanism of the phase change process. After the test is completed, the temperature can be slowly increased by the temperature control system to achieve reverse detection of the liquid-solid phase change process. Before the experiment starts, the test background pressure in the measurement cavity is changed, and the liquid-solid transformation process under different pressure conditions can be tested and studied.

[0072] Figure 2 The preprocessing and fusion analysis process of multi-source information is briefly presented. The data cross-fusion between different detection methods is realized mainly through the preprocessing, normalization and correlation analysis of multi-source information, and is used together for the quantitative analysis of the liquid-solid phase change process of the fluid to be tested. It mainly includes the basic analysis process such as data conversion of morphological image information, normalization of light transmittance, phase change temperature and phase change pressure, unified classification of multiple information, and correlation analysis between morphological characteristics and quantitative parameters. Among them, the image information collected by the electron microscope probe is used to intuitively reflect the morphological characteristics such as aggregation, arrangement, and crystallization of molecules in the liquid-solid phase change. The convolutional neural network algorithm should be used to convert the image information into a one-dimensional array by extracting characteristic variables, and then the array elements are normalized by combining the normalization algorithm; for transmittance, phase change temperature and pressure variables with different units and magnitudes, the normalization algorithm should be used to find standardized parameters and convert all data to the same interval. Taking the real-time time recorded by the electronic timer as the benchmark, the light transmittance, phase change temperature, phase change pressure and the different development stages of the phase change morphological characteristics are classified and corresponded to achieve cross-fusion of all characteristic parameters. On this basis, the BP neural network algorithm is further used to study the mathematical relationship between all characteristic variables, that is, the measurement model of the new liquid-solid phase change detection device.

[0073] Since there are significant differences in the units, magnitudes, intervals and types of signals measured by different sensors, it is necessary to convert them to the same standard with the same time reference benchmark, and then conduct information classification, cross-fusion and research and analysis. Among them, the image used to intuitively reflect the morphology of the phase change process should first be extracted through a convolutional neural network to extract a one-dimensional array, and then the image information should be converted into one-dimensional feature data in combination with a normalization algorithm; the light transmittance, phase change temperature and phase change pressure in the phase change process should first determine the parameters that can be used for standardization, and then perform dimensionless processing to convert them into standard values ​​between 0 and 1. Further, with the same time reference benchmark, all information is uniformly classified according to the morphological characteristics of different phase change processes; based on the morphological characteristics of liquid-solid phase change, the other three characteristic variables are used to quantitatively analyze the morphological characteristics, and the mathematical relationship between the morphological characteristics and light transmittance, phase change temperature and phase change pressure is obtained.

[0074] The process of extracting morphological image feature values ​​using convolutional neural networks is as follows: Figure 3 shown.

[0075] According to the solid morphology under the electron microscope, a convolution kernel is established to identify solid phase crystals and their arrangement. The image of the morphology of the object under test in the measurement cavity is input, and the convolution kernel and the digital information of the image are used to convolve the input image to generate a convolution layer matrix. Subsequently, a pooling program is used to reduce the image and retain important information. After multiple layers of convolution and pooling, the ReLU function is used as shown in formula (1) to activate the final pooling layer.

[0076] f(x)=max(0,x) (1)

[0077] The activated matrix contains the main information of the morphological image. The activated matrix is ​​flattened, the matrix is ​​converted into a one-dimensional vector, and then the phase change morphological feature data is output in the form of a one-dimensional array.

[0078] Figure 4 The liquid-solid phase transition morphological characteristic measurement model constructed using the BP neural network algorithm is demonstrated. After determining the input and output variables, the input and output data are normalized using the Min-Max normalization method so that the normalized value range is dimensionless within 0 to 1:

[0079]

[0080] In the formula, Z represents the input variable or output variable, Z max and Z min Represent the maximum and minimum values ​​respectively.

[0081] With light transmittance, phase change temperature, and phase change pressure as input quantities, the characteristic parameters of light transmittance, phase change temperature, and phase change pressure measured by the sensor are used to extract the real and effective target signal through Fourier transform. The three characteristic parameters are used as input variables and preprocessed, and converted into dimensionless variables through normalization to reduce the gradient of the data and accelerate the convergence speed of the model. The preprocessed input variables are input into the constructed BP neural network for training and constructing a measurement model for judging the morphological characteristics of liquid-solid phase change.

[0082] When constructing a liquid-solid phase change morphological feature measurement model using a machine learning algorithm, standard materials are used for calibration in a stable test environment. During the calibration process, an electron microscope is used to photograph the phase change process of the material being measured in the measurement cavity, and manual intervention is performed on the photographed phase change process images and the various states of the transformation process. At the same time, the various data in the measurement cavity detected by the three sensors when each image is taken are recorded. The image taken by the electron microscope is used to extract the phase change morphological feature data through a convolutional neural network, and it is used as the output group. The three sensor data recorded at the time corresponding to each image are used as the input group and input into the BP neural network for model training.

[0083] After the training is completed, 20% of the screen images and the corresponding three sensor data are selected to verify the accuracy of the model. After inputting the data of the three sensors at the corresponding moment, the BP neural network is used to judge the phase change state and compare it with the feature data and content of the screen. If the accuracy rate is greater than 95%, the model verification is completed. In the established model for judging the liquid-solid phase change state, light transmittance, phase change temperature and phase change pressure are used as input variables, and phase change morphological characteristics are used as output variables.

[0084] The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A sample liquid-solid phase change detection device, characterized in that: include: A measuring cavity, wherein the measuring cavity is arranged inside the detection box, and a plurality of light sources are installed on the top of the measuring cavity; a liquid inlet, a pressurization port and a plurality of sensor installation ports connected to the measuring cavity are provided on the top of the detection box, a liquid discharge port connected to the measuring cavity is provided on the bottom of the detection box, and corresponding observation windows are provided on the front side wall of the measuring cavity and the front side wall of the detection box; A laser sensor unit, comprising a laser sensor transmitting module and a laser sensor receiving module, wherein the laser sensor transmitting module and the laser sensor receiving module are symmetrically arranged on the left and right sides of the detection box; A sensor group, including a temperature sensor and a pressure sensor, wherein the temperature sensor and the pressure sensor are installed in corresponding sensor installation ports; A camera module, the camera module is arranged at one side of the detection box and corresponds to the position of the front side wall of the detection box; The control unit includes a main controller and a signal excitation module, a timing module, a data acquisition module and a temperature control module electrically connected to the main controller; the camera module, the laser sensor unit and the sensor group are all electrically connected to the data acquisition module, the signal excitation module is also electrically connected to the laser sensor emission module, and the detection box is electrically connected to the temperature control module.

2. A sample liquid-solid phase change detection device according to claim 1, characterized in that: A constant temperature medium layer and a heat preservation layer are sequentially arranged between the outer wall of the measuring cavity and the inner wall of the detection box.

3. A sample liquid-solid phase change detection device according to claim 2, characterized in that: A constant temperature medium inlet is provided on the outer side wall of the detection box body, and the constant temperature medium inlet passes through the thermal insulation layer and is communicated with the constant temperature medium layer.

4. A sample liquid-solid phase change detection device according to claim 2, characterized in that: Each laser transmitter in the laser sensor transmitting module is arranged in one-to-one correspondence with each laser receiver in the laser sensor receiving module. Each laser transmitter is connected to the signal excitation module, and each laser receiver is connected to the data acquisition module.

5. A sample liquid-solid phase change detection method, applied to a sample liquid-solid phase change detection device according to any one of claims 1 to 4, characterized in that: include: Step 1: Filling the measurement cavity with a sample to be tested, wherein the sample to be tested is in a fluid state; Step 2: Turn on the sample liquid-solid phase change detection device, measure the phase change state of the sample to be tested in combination with a preset temperature, and record the measurement data, the measurement data including light transmittance data, morphological image data, phase change temperature data and phase change pressure data; Step three: input the measurement data into a phase change detection model integrated in the main controller to perform feature detection to obtain phase change morphological feature data, wherein the phase change detection model is constructed based on a BP neural network.

6. A sample liquid-solid phase change detection method according to claim 5, characterized in that: The process of obtaining the measurement data specifically includes: The temperature control module is controlled to cool the sample to be tested until the sample to be tested is cooled to a preset fluid crystallization point threshold, and then the temperature is lowered; in the process of cooling the sample to be tested, the signal excitation module is used to excite the laser sensor unit to obtain light transmittance data; the camera module is used to obtain the morphological image data of the sample to be tested in the measuring cavity, the temperature sensor is used to obtain the phase change temperature data, and the pressure sensor is used to obtain the phase change pressure data.

7. A sample liquid-solid phase change detection method according to claim 5, characterized in that: Before inputting the measurement data into the phase change detection model, the method further includes: Performing feature extraction on the morphological image data to obtain image feature data; The light transmittance data, phase change temperature data and phase change pressure data are normalized based on the time series to obtain normalized data, the normalized data and the image feature data are converted into one-dimensional matrix data to obtain preprocessed measurement data, and the preprocessed measurement data is used as the input of the phase change detection model for feature detection.

8. A sample liquid-solid phase change detection method according to claim 5, characterized in that: The training process of the phase change detection model specifically includes: Acquiring training data, wherein the training data includes measurement training data and corresponding phase change morphology characteristic data; An initial phase change detection model is constructed, the training data is input into the initial phase change detection model, the light transmittance data, phase change temperature data and phase change pressure data are used to quantitatively analyze the characteristics of the morphological image data to obtain initial phase change morphological feature data, and training is performed with the goal of minimizing the loss between the initial phase change morphological feature data and the phase change morphological feature data corresponding to the measured training data to obtain a trained phase change detection model.

Images