Polymer slurry viscosity detection method and device based on slump method

Abstract

The invention relates to a polymer slurry viscosity detection method and device based on a slump method, and belongs to the technical field of polymer material detection.The method comprises the steps that in the dispersion process of polymer slurry, slump parameters of the polymer slurry are obtained; the slump parameters comprise slump time, sample temperature, slump speed and slump breadth; inputting the slump parameters into a trained prediction model to obtain predicted viscosity of the polymer slurry output by the prediction model; the prediction model is obtained by training the BP neural network based on the collapse parameters of the standard sample. The polymer slurry viscosity detection method based on the slump method provided by the invention has the advantages of small sample consumption in the detection process, low cost, sustainable slurry dispersion process in the detection process, real-time detection and feedback of the slump speed and breadth of the polymer slurry under the dead weight based on the slump method and the neural network algorithm, and accurate detection of the viscosity of the polymer slurry. The predicted viscosity of the polymer slurry can be accurately measured in real time, and the detection speed is high.

Description

Technical Field

[0001] This invention relates to the field of polymer material testing technology, and in particular to a method and apparatus for testing the viscosity of polymer slurries based on the slump test. Background Technology

[0002] Liquid slurries possess certain viscosity characteristics and flowability. For some polymeric slurries, such as platinum-carbon catalyst slurries used in the fuel cell industry, viscosity characteristics are crucial for industrial production and performance breakthroughs. The dispersion process and method of polymeric slurries have a profound impact on slurry uniformity and viscosity; these three factors interact to jointly determine the slurry's state.

[0003] Existing methods use a dual-rotor structure to adaptively calculate slurry viscosity at different shear rates. This method is very similar to the traditional method using a rheometer, which cannot achieve rapid online functionality and results in significant slurry waste.

[0004] Currently, the slurry dispersion process mostly relies on experience-based adjustments, while viscosity testing often uses equipment such as rheometers, which are costly, have low data acquisition efficiency, and fail to provide real-time feedback on the dispersion process. Summary of the Invention

[0005] In view of this, it is necessary to provide a method and apparatus for detecting the viscosity of polymer slurries based on the slump method, so as to reduce the detection efficiency of polymer slurry viscosity.

[0006] To achieve the above objectives, in a first aspect, the present invention provides a method for detecting the viscosity of polymer slurry based on the slump test, comprising: During the dispersion process of polymer slurry, the slump parameters of the polymer slurry are obtained; the slump parameters include slump time, sample temperature, slump rate, and slump extent. The collapse parameters are input into the trained prediction model to obtain the predicted viscosity of the polymer slurry output by the prediction model; the prediction model is obtained by training a BP neural network based on the collapse parameters of standard samples.

[0007] In one possible implementation, after inputting the collapse parameters into the trained prediction model to obtain the predicted viscosity of the polymer slurry output by the prediction model, the method further includes: The dispersion time of the dispersion process is controlled based on the preset viscosity and the predicted viscosity.

[0008] In one possible implementation, controlling the dispersion time of the dispersion process based on the preset viscosity and the predicted viscosity includes: When the predicted viscosity is lower than the preset viscosity, the dispersion time is increased; The dispersion process is stopped when the predicted viscosity equals the preset viscosity.

[0009] In one possible implementation, the prediction model includes an input layer, a hidden layer, and an output layer; The step of inputting the collapse parameters into the trained prediction model to obtain the predicted viscosity of the polymer slurry output by the prediction model includes: The input collapse parameters are preprocessed using the input layer. The hidden layer is used to perform weighted and activation operations on the preprocessed collapse parameters; The predicted viscosity is output using the output layer.

[0010] In one possible implementation, obtaining the slump parameters of the polymer slurry during the dispersion process includes: When the dispersion process is a high-pressure closed dispersion, the slump parameters are obtained by quantitative titration of the polymer slurry after the dispersion process is stopped. When the dispersion process is a low-speed, atmospheric-pressure dispersion, the slump parameters are obtained by quantitative titration of the polymer slurry during the dispersion process.

[0011] Secondly, the present invention also provides a polymer slurry viscosity detection device based on the slump test, comprising: The acquisition unit acquires the slump parameters of the polymer slurry during the dispersion process; the slump parameters include slump time, sample temperature, slump rate, and slump extent. The prediction unit inputs the collapse parameters into the trained prediction model to obtain the predicted viscosity of the polymer slurry output by the prediction model; the prediction model is obtained by training a BP neural network based on the collapse parameters of standard samples.

[0012] Thirdly, the present invention also provides an electronic device, including a memory and a processor, wherein, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the polymer slurry viscosity detection method based on the slump method described in any of the above implementations.

[0013] Fourthly, the present invention also provides a polymer slurry viscosity detection system based on the slump test method, comprising the electronic equipment described in any of the above implementations, and further comprising: Dispersion equipment, quantitative titration pump, testing platform, and high-speed vision camera; The quantitative titration pump and the dispersion device are connected by pipelines; The test platform is positioned directly below the quantitative titration pump body; The high-speed vision camera is positioned directly below the test platform; The dispersion equipment is used to perform the dispersion process of polymer slurry; The quantitative titration pump is used to quantitatively titrate the polymer slurry onto the test platform; The high-speed vision camera is used to acquire the slump time, slump speed, and slump extent of the polymer slurry during the titration process.

[0014] In one possible implementation, the test platform is circular in shape; the test platform is made of transparent material; and the test platform is provided with scale dimensions.

[0015] In one possible implementation, when the dispersion process is a high-pressure closed dispersion, the dispersion equipment needs to be shut down during the titration process; When the dispersion process is a low-speed, atmospheric-pressure dispersion, the dispersion equipment does not need to be stopped during the titration process.

[0016] Fifthly, the present invention also provides a computer-readable storage medium for storing a computer-readable program or instructions, which, when executed by a processor, can implement the steps in the polymer slurry viscosity detection method based on the slump method described in any of the above implementations.

[0017] The beneficial effects of this invention are as follows: The polymer slurry viscosity detection method and apparatus based on the slump method provided by this invention quantitatively titrates the polymer slurry during the dispersion process. The detection process consumes a small amount of sample, resulting in low cost. It obtains the slump time, sample temperature, slump rate, and slump extent of the polymer slurry during the titration process. The slurry dispersion process is continuous during the detection process. The slump parameters are analyzed using big data using neural networks. Starting from the viscosity and flow characteristics of the polymer slurry, based on the slump method and neural network algorithm, the slump rate and extent of the polymer slurry under its own weight are detected and fed back in real time. Combined with the calibration sample results and neural network big data statistical analysis, the predicted viscosity of the polymer slurry can be accurately calculated in real time, and the detection speed is fast. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1This is a schematic flowchart of an embodiment of the polymer slurry viscosity detection method based on the slump test provided by the present invention. Figure 2 A schematic diagram illustrating the process of applying the slump-based viscosity detection method for polymer slurries provided by this invention; Figure 3 A schematic diagram of an embodiment of the polymer slurry viscosity detection device based on the slump method provided by the present invention; Figure 4 A schematic diagram of an embodiment of the electronic device provided by the present invention; Figure 5 This is a schematic diagram of an embodiment of the polymer slurry viscosity detection system based on the slump method provided by the present invention.

[0020] Figure label: 1: Dispersion equipment; 2: Quantitative titration pump; 3: Test platform; 4: High-speed vision camera. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0022] In the description of the embodiments of the present invention, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0023] The terms "first," "second," etc., used in the embodiments of this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a technical feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature.

[0024] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0025] This invention provides a method and apparatus for detecting the viscosity of polymer slurry based on the slump test, which will be described below.

[0026] Figure 1 This is a schematic flowchart of an embodiment of the polymer slurry viscosity detection method based on the slump test provided by the present invention, as shown below. Figure 1 As shown, the viscosity detection method for polymer slurries based on the slump test includes: S101. During the dispersion process of the polymer slurry, the slump parameters of the polymer slurry are obtained; the slump parameters include slump time, sample temperature, slump rate, and slump extent. S102. Input the collapse parameters into the trained prediction model to obtain the predicted viscosity of the polymer slurry output by the prediction model; the prediction model is obtained by training a BP neural network based on the collapse parameters of standard samples.

[0027] It should be noted that this invention is applicable to the viscosity calculation and control of polymer slurries, such as the viscosity state detection of catalyst slurries in the field of fuel cells. It can be applied to the industrial rapid detection and production quality control of polymer dispersion systems (such as platinum-carbon catalyst slurries for fuel cells, nanomaterial suspensions, etc.).

[0028] In S101, during the dispersion of the polymer slurry, the polymer slurry is quantitatively titrated. Utilizing the effects of the polymer slurry's own weight, viscosity, or rheological properties, slump parameters during the titration process are obtained. These slump parameters include slump time, sample temperature, slump rate, and slump extent. The slump rate and extent can be captured by a high-speed vision camera, and the slump time and sample temperature of the polymer slurry can also be obtained.

[0029] Slurries of the same volume but different viscosities and fluid properties will have different slump heights and widths under their own weight within a specified time, which makes it easier to summarize and distinguish the relationship between the two.

[0030] In S102, the backpropagation (BP) neural network is pre-trained using standard samples in terms of time, speed, extent, and temperature during the collapse process to obtain a trained prediction model. The BP neural network is a multi-layer feedforward neural network trained according to the error backpropagation algorithm.

[0031] Standard samples can be deionized water, ethanol, or ethylene glycol, etc., so that the prediction model can be used to perform big data analysis on the collapse parameters and output the predicted viscosity of the polymer slurry.

[0032] In summary, the polymer slurry viscosity detection method based on the slump method provided in this embodiment of the invention quantitatively titrates the polymer slurry during the dispersion process. This method consumes a small amount of sample, resulting in low cost. It obtains the slump time, sample temperature, slump rate, and slump extent of the polymer slurry during titration. The slurry dispersion process is continuous during detection, and a neural network is used to perform big data analysis on the slump parameters. Starting from the viscosity and flow characteristics of the polymer slurry, based on the slump method and neural network algorithm, the slump rate and extent of the polymer slurry under its own weight are detected and fed back in real time. Combining the calibration sample results and neural network big data statistical analysis, the predicted viscosity of the polymer slurry can be accurately calculated in real time, resulting in fast detection speed.

[0033] In some embodiments of the present invention, after inputting the collapse parameters into the trained prediction model to obtain the predicted viscosity of the polymer slurry output by the prediction model, the method further includes: The dispersion time of the dispersion process is controlled based on the preset viscosity and the predicted viscosity.

[0034] In some embodiments of the present invention, controlling the dispersion time of the dispersion process based on the preset viscosity and the predicted viscosity includes: When the predicted viscosity is lower than the preset viscosity, the dispersion time is increased; The dispersion process is stopped when the predicted viscosity equals the preset viscosity.

[0035] For example, after the dispersion process lasts for 10 minutes, if the predicted viscosity is 5 mPa·s and the preset viscosity is 10 mPa·s, that is, the predicted viscosity is lower than the preset viscosity, then the dispersion needs to continue until the predicted viscosity equals the preset viscosity. At this point, the dispersion is successful and the dispersion stops, thus achieving the effect of real-time feedback during the dispersion process.

[0036] In some embodiments of the present invention, the prediction model includes an input layer, a hidden layer, and an output layer; The step of inputting the collapse parameters into the trained prediction model to obtain the predicted viscosity of the polymer slurry output by the prediction model includes: The input collapse parameters are preprocessed using the input layer. The hidden layer is used to perform weighted and activation operations on the preprocessed collapse parameters; The predicted viscosity is output using the output layer.

[0037] Figure 2 A schematic diagram of the process for applying the slump-based viscosity detection method for polymer slurries provided by this invention is shown below. Figure 2 As shown, a neural network is trained using parameters from standard samples to achieve functions such as slurry viscosity prediction, including the following steps: Obtain the collapse parameters (collapse time, temperature, extent, and speed) of standard samples such as deionized water, ethanol, and ethylene glycol, and form a database.

[0038] According to the model input layer requirements, the test sample collapse parameters and standard sample database are input. The input collapse parameters are then preprocessed, such as normalization, to convert the data into a range that the network can process.

[0039] The database of standard samples serves as the training data for the neural network, and is divided into a training set and a validation set.

[0040] The training set is used to perform weighted summaries and activation function operations on the hidden layer to simulate the relationship between parameters. The accuracy of the model is then verified using the validation set. The parameters are adjusted until the accuracy reaches the target, thus completing the training.

[0041] The weighted operation multiplies the input layer values ​​by different weights and then sums them up. The weights are parameters adjusted during model training and represent the degree of influence of the input on the output.

[0042] Activation functions (Sigmoid, ReLU) introduce non-linearity into the weighted results, enabling the model to learn complex relationships.

[0043] Weighted operations and activation function operations can ensure that the hidden layer extracts and processes key features, and outputs the final predicted viscosity.

[0044] After the model is trained, inputting slump parameters can predict the slurry viscosity in real time, while providing dispersion suggestions (such as adjusting the dispersant, stirring parameters, and dispersion time) and state assessment (determining whether the dispersion is uniform and whether the system is stable), assisting in the control of slurry performance during the dispersion process.

[0045] In some embodiments of the present invention, obtaining the slump parameters of the polymer slurry during the dispersion process includes: When the dispersion process is a high-pressure closed dispersion, the slump parameters are obtained by quantitative titration of the polymer slurry after the dispersion process is stopped. When the dispersion process is a low-speed, atmospheric-pressure dispersion, the slump parameters are obtained by quantitative titration of the polymer slurry during the dispersion process.

[0046] The dispersion method used in the dispersion process will affect whether the dispersion needs to be paused during slurry testing.

[0047] When the dispersion process is a high-pressure closed dispersion, it is necessary to control the dispersion process to be paused before quantitative titration of the polymer slurry.

[0048] When the dispersion process is a low-speed, atmospheric-pressure dispersion, there is no need to control the dispersion process to pause; the polymer slurry can be quantitatively titrated directly during the dispersion process.

[0049] To better implement the polymer slurry viscosity detection method based on the slump method in the embodiments of the present invention, based on the polymer slurry viscosity detection method based on the slump method, correspondingly, as follows: Figure 3 As shown, this embodiment of the invention also provides a polymer slurry viscosity testing device based on the slump test. The polymer slurry viscosity testing device 300 based on the slump test includes: The acquisition unit 301 acquires the slump parameters of the polymer slurry during the dispersion process; the slump parameters include slump time, sample temperature, slump rate, and slump extent. The prediction unit 302 inputs the collapse parameters into the trained prediction model to obtain the predicted viscosity of the polymer slurry output by the prediction model; the prediction model is obtained by training a BP neural network based on the collapse parameters of standard samples.

[0050] The polymer slurry viscosity testing device 300 based on the slump method provided in the above embodiments can realize the technical solutions described in the embodiments of the polymer slurry viscosity testing method based on the slump method. The specific implementation principles of each module or unit can be found in the corresponding content in the embodiments of the polymer slurry viscosity testing method based on the slump method, and will not be repeated here.

[0051] like Figure 4 As shown, the present invention also provides an electronic device 400. The electronic device 400 includes a processor 401, a memory 402, and a display 403. Figure 4 Only some components of the electronic device 400 are shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

[0052] In some embodiments, processor 401 may be a central processing unit (CPU), microprocessor, or other data processing chip, used to run program code stored in memory 402 or process data, such as the polymer slurry viscosity detection method based on slump test in this invention.

[0053] In some embodiments, processor 401 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 401 may be local or remote. In some embodiments, processor 401 may be implemented on a cloud platform. In some embodiments, the cloud platform may include a private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, internal cloud, multi-cloud, or any combination thereof.

[0054] In some embodiments, memory 402 may be an internal storage unit of electronic device 400, such as a hard disk or memory of electronic device 400. In other embodiments, memory 402 may also be an external storage device of electronic device 400, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on electronic device 400.

[0055] Furthermore, the memory 402 may include both internal storage units of the electronic device 400 and external storage devices. The memory 402 is used to store application software and various types of data installed on the electronic device 400.

[0056] In some embodiments, display 403 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an organic light-emitting diode (OLED) touchscreen. Display 403 is used to display information from electronic device 400 and to display a visual user interface. Components 401-403 of electronic device 400 communicate with each other via a system bus.

[0057] In one embodiment, when processor 401 executes a polymer slurry viscosity detection program based on slump test in memory 402, the following steps can be implemented: During the dispersion process of polymer slurry, the slump parameters of the polymer slurry are obtained; the slump parameters include slump time, sample temperature, slump rate, and slump extent. The collapse parameters are input into the trained prediction model to obtain the predicted viscosity of the polymer slurry output by the prediction model; the prediction model is obtained by training a BP neural network based on the collapse parameters of standard samples.

[0058] Furthermore, this embodiment of the invention does not specifically limit the type of electronic device 400 mentioned. Electronic device 400 can be a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, laptop computer, or other portable electronic device. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the invention, electronic device 400 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0059] This invention also provides a polymer slurry viscosity detection system based on the slump test, comprising the electronic equipment described in any of the above implementations, and further: 1. Dispersion device; 2. Quantitative titration pump body; 3. Test platform; and 4. High-speed vision camera; The quantitative titration pump body 2 and the dispersion device 1 are connected by pipelines; The test platform 3 is located directly below the quantitative titration pump body 2; The high-speed vision camera 4 is positioned directly below the test platform 3; The dispersion device 1 is used to perform the dispersion process of the polymer slurry; The quantitative titration pump body 2 is used to quantitatively titrate the polymer slurry onto the test platform 3; The high-speed vision camera 4 is used to acquire the slump time, slump speed and slump extent of the polymer slurry during the titration process.

[0060] Figure 5 This is a schematic diagram of an embodiment of the polymer slurry viscosity detection system based on the slump method provided by the present invention. See also: Figure 5 The polymer slurry viscosity testing system based on the slump method includes a dispersion device 1, a quantitative titration pump 2, a test platform 3, and a high-speed vision camera 4.

[0061] First, a polymer slurry is prepared and dispersed in dispersion equipment 1.

[0062] To achieve a method for real-time viscosity detection, the dispersion device 1 is connected to the quantitative titration pump 2 via a pipeline.

[0063] The slurry can be quantitatively titrated onto the test platform 3 via the quantitative titration pump 2, with the titration position at the center of the test platform. Preferably, the titration of the slurry should be quantitative and can be controlled and modified by a program.

[0064] A high-speed vision camera 4 is installed directly below the test platform 3 to record the titration process and slurry slump process at specified times. The pixel count and processing power of the high-speed vision camera 4 have a significant impact on viscosity measurement.

[0065] Before the system products are officially put into use, it is necessary to calculate the viscosity characteristics and collapse rate of calibration materials such as liquid water, alcohols, and standard polymer materials to form a large database.

[0066] The slump rate and extent of the slurry are strongly correlated with the product viscosity, and the titration pump should be linked to a vision device to increase accuracy.

[0067] Based on the titration slump results, analysis and comparison are performed. Slump parameters (such as slump rate and extent at a specific experimental time) along with previous standard sample parameters are input into the neural network input layer. The viscosity of the slurry is obtained by calculation and prediction through the neural network.

[0068] The analysis results obtained by the system can be compared with the target value to guide the dispersion process of the dispersion device 1, thereby realizing the function of real-time feedback.

[0069] Understandably, the system has built-in collapse parameters for standard samples, such as deionized water, common alcohols, and other standard high-molecular organic liquids, to perform big data statistical analysis and artificial intelligence classification, thereby obtaining the viscosity data of the sample to be tested.

[0070] The polymer slurry viscosity detection system based on the slump method provided in this invention quantitatively titrates the polymer slurry during the dispersion process onto a graduated measuring platform. Utilizing the slurry's own weight and the influence of viscosity and rheology, a high-speed visual camera captures the slump speed and extent. By comparing calibration sample data and previous measurement data, and through neural network prediction using a big data model, the viscous characteristics of the slurry are obtained. These characteristics are then fed back into the slurry dispersion process to achieve optimized dispersion. This method is simple, efficient, low-cost, and enables real-time detection.

[0071] In some embodiments of the present invention, the test platform 3 is circular in shape; the test platform 3 is made of transparent material; and the test platform 3 is provided with scale dimensions.

[0072] Test platform 3 is made of a circular, highly transparent material and has graduated dimensions. It also has anti-corrosion and anti-acid properties.

[0073] A quantitative slurry is pumped out from the dispersion device and titrated onto the detection platform. A high-speed vision camera can detect the slump time, speed, and extent of the slurry within a specified time.

[0074] A high-speed vision camera is installed directly below the test platform to record the titration process and the slurry slump process at specified times.

[0075] In some embodiments of the present invention, when the dispersion process is a high-pressure closed dispersion, the dispersion equipment 1 needs to be shut down during the titration process; When the dispersion process is a low-speed, atmospheric-pressure dispersion, the dispersion equipment 1 does not need to be stopped during the titration process.

[0076] The dispersion method affects whether the dispersion needs to be paused during the slurry measurement process.

[0077] If the dispersion method is low-speed atmospheric pressure dispersion, the quantitative titration pump body 2 will not affect the dispersion process when feeding materials.

[0078] If the dispersion method is high-pressure closed dispersion, the titration process requires the dispersion equipment 1 to be shut down before it can be carried out.

[0079] The following describes in detail the polymer slurry viscosity detection method based on the slump test provided by this invention, with specific application scenarios. This invention provides a method for real-time detection and control of fuel cell catalyst slurry viscosity, the main steps of which include: S1. To obtain a certain fuel cell platinum-carbon catalyst slurry with a viscosity of 10 mPa·s, platinum-carbon, deionized water, ethanol, and perfluorosulfonic acid resin are prepared in a certain proportion and placed in a stirring and dispersing device. The bottom of the stirring and dispersing device is connected to a titration pump through a pipeline.

[0080] S2. After dispersing for 10 minutes, turn on the titration pump and quantitatively titrate 1 mL of slurry onto the test platform. After the slurry titration is completed, the high-speed vision camera immediately records and forms a neural network input parameter table, as shown in Table 1.

[0081] Table 1: Neural Network Input Parameter Table

[0082] S3. Input the input parameters into the neural network and calculate that the viscosity of the dispersed slurry is 5 mPa·s, which is lower than the target value, so continue dispersing.

[0083] S4. After dispersing for 10 minutes, 1 mL of slurry was quantitatively titrated onto the test platform. After the slurry titration was completed, the high-speed vision camera immediately recorded the data and compared it with the existing slump rate and width of the system. The viscosity of the dispersed slurry at this time was found to be 10 mPa·s, so the dispersion was successful.

[0084] This invention combines the simplicity of the slump test with the real-time detection and control of polymer dispersion processes. It utilizes big data for neural network analysis to achieve real-time viscosity calculation, thus overcoming the shortcomings of insufficient research on the dynamic correlation between dispersant formulation and viscosity parameters, and solving the problems of existing viscosity testing such as lag, high cost, and long time.

[0085] Accordingly, embodiments of the present invention also provide a computer-readable storage medium for storing computer-readable programs or instructions. When the programs or instructions are executed by a processor, they can implement the steps or functions of the polymer slurry viscosity detection method based on the slump method provided in the above-described method embodiments.

[0086] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.), and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0087] The above provides a detailed description of the polymer slurry viscosity detection method and apparatus based on the slump test method provided by the present invention. Specific examples have been used to illustrate the principle and implementation of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation and application scope based on the idea of ​​the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for detecting the viscosity of polymer slurry based on the slump test, characterized in that, include: During the dispersion process of polymer slurry, the slump parameters of the polymer slurry are obtained; the slump parameters include slump time, sample temperature, slump rate, and slump extent. The collapse parameters are input into the trained prediction model to obtain the predicted viscosity of the polymer slurry output by the prediction model; the prediction model is obtained by training a BP neural network based on the collapse parameters of standard samples.

2. The method for detecting the viscosity of polymer slurry based on the slump test according to claim 1, characterized in that, After inputting the collapse parameters into the trained prediction model to obtain the predicted viscosity of the polymer slurry output by the prediction model, the method further includes: The dispersion time of the dispersion process is controlled based on the preset viscosity and the predicted viscosity.

3. The method for detecting the viscosity of polymer slurry based on the slump test according to claim 2, characterized in that, The control of the dispersion time based on the preset viscosity and the predicted viscosity includes: When the predicted viscosity is lower than the preset viscosity, the dispersion time is increased; The dispersion process is stopped when the predicted viscosity equals the preset viscosity.

4. The method for detecting the viscosity of polymer slurry based on the slump test according to claim 1, characterized in that, The prediction model includes an input layer, a hidden layer, and an output layer; The step of inputting the collapse parameters into the trained prediction model to obtain the predicted viscosity of the polymer slurry output by the prediction model includes: The input collapse parameters are preprocessed using the input layer. The hidden layer is used to perform weighted and activation operations on the preprocessed collapse parameters; The predicted viscosity is output using the output layer.

5. The method for detecting the viscosity of polymer slurry based on the slump test according to claim 1, characterized in that, The process of obtaining the slump parameters of the polymer slurry during dispersion includes: When the dispersion process is a high-pressure closed dispersion, the slump parameters are obtained by quantitative titration of the polymer slurry after the dispersion process is stopped. When the dispersion process is a low-speed, atmospheric-pressure dispersion, the slump parameters are obtained by quantitative titration of the polymer slurry during the dispersion process.

6. A polymer slurry viscosity testing device based on the slump test, characterized in that, include: The acquisition unit acquires the slump parameters of the polymer slurry during the dispersion process; the slump parameters include slump time, sample temperature, slump rate, and slump extent. The prediction unit inputs the collapse parameters into the trained prediction model to obtain the predicted viscosity of the polymer slurry output by the prediction model; the prediction model is obtained by training a BP neural network based on the collapse parameters of standard samples.

7. An electronic device, characterized in that, Including memory and processor, among which, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the polymer slurry viscosity detection method based on the slump method as described in any one of claims 1 to 5.

8. A polymer slurry viscosity detection system based on the slump test, comprising the electronic device described in claim 7, characterized in that, Also includes: Dispersion equipment, quantitative titration pump, testing platform, and high-speed vision camera; The quantitative titration pump and the dispersion device are connected by pipelines; The test platform is positioned directly below the quantitative titration pump body; The high-speed vision camera is positioned directly below the test platform; The dispersion equipment is used to perform the dispersion process of polymer slurry; The quantitative titration pump is used to quantitatively titrate the polymer slurry onto the test platform; The high-speed vision camera is used to acquire the slump time, slump speed, and slump extent of the polymer slurry during the titration process.

9. The polymer slurry viscosity detection system based on the slump test method according to claim 8, characterized in that, The test platform is circular in shape; the test platform is made of transparent material; and the test platform is equipped with scale dimensions.

10. The polymer slurry viscosity detection system based on the slump test method according to claim 8, characterized in that, When the dispersion process is a high-pressure closed dispersion, the dispersion equipment needs to be shut down during the titration process; When the dispersion process is a low-speed, atmospheric-pressure dispersion, the dispersion equipment does not need to be stopped during the titration process.

Images