Method, device and equipment for detecting apparent viscosity of material and medium

Abstract

The invention relates to the technical field of artificial intelligence, and discloses a material apparent viscosity detection method, device, equipment and medium, firstly, a target apparent viscosity detection model corresponding to current stirring equipment is determined, and a training sample of the model is constructed based on test data collected in the process of testing the stirring equipment to stir a Newtonian fluid material; the test stirring equipment and the current stirring equipment have the same equipment parameters. Then, the detection stirring rotating speed and the detection stirring torque of a to-be-detected material in the current stirring equipment are obtained, wherein the to-be-detected material can be a Newtonian fluid material or a non-Newtonian fluid material; finally, the detected stirring rotating speed and the detected stirring torque are input into the target apparent viscosity detection model for reasoning, and the apparent viscosity of the to-be-detected material is obtained. According to the method, sampling is not needed, in-situ online detection of the apparent viscosity of the material is achieved, and the overall apparent viscosity of the material in the stirring equipment can be reflected in real time.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, device, equipment and medium for detecting the apparent viscosity of a material. Background Art

[0002] The apparent viscosity of materials is a key process parameter in the chemical production process, which directly affects the fluidity of materials, heat and mass transfer, and the efficiency of chemical reactions. In related technologies, the detection of the apparent viscosity of materials relies on offline detection. After sampling, a rheometer is used to measure the rheological behavior of the sample. Although offline detection can provide detailed information on the rheological properties of the sample, during the sampling process, the material may undergo gelation, emulsion or suspension phase separation, resulting in changes in sample consistency, thereby affecting the accuracy of the test results. Therefore, it is urgent to propose a new method for detecting the apparent viscosity of materials. Summary of the invention

[0003] The present application provides a method, device, equipment and medium for detecting the apparent viscosity of a material, which solves the technical problem in the related art that the accuracy of detecting the apparent viscosity of a material needs to be improved, and achieves the technical effect of more accurately detecting the apparent viscosity of a material.

[0004] In order to achieve the above objectives, the main technical solutions adopted in this application include: In a first aspect, an embodiment of the present application provides a method for detecting the apparent viscosity of a material, the method comprising: Determine a target apparent viscosity detection model corresponding to the current stirring device; wherein the training sample of the target apparent viscosity detection model is constructed based on test data collected during the process of stirring a Newtonian fluid material with the test stirring device; the test stirring device and the current stirring device have the same device parameters; Acquire the detection stirring speed and detection stirring torque of the material to be detected in the current stirring device; wherein the material to be detected is a Newtonian fluid material or a non-Newtonian fluid material; The detected stirring speed and the detected stirring torque are input into the target apparent viscosity detection model for inference to obtain the apparent viscosity of the material to be detected.

[0005] Optionally, determining a target apparent viscosity detection model corresponding to the current stirring device includes: Obtaining the target device type of the current mixing device; The apparent viscosity detection model corresponding to the target device type is determined as the target apparent viscosity detection model.

[0006] Optionally, the liquid level of the material to be detected in the current stirring device reaches a preset height; and the step of obtaining the detected stirring speed and the detected stirring torque of the material to be detected in the current stirring device includes: When the liquid level of the material to be detected reaches the preset height, the detected stirring speed and the detected stirring torque are obtained.

[0007] Optionally, the current stirring device is configured with a motor and a stirrer; the motor is used to drive the stirrer to stir the material to be detected, so that the material to be detected is in a laminar flow state; The detection stirring speed is the speed of the material to be detected in a laminar flow state; The detection stirring torque is the torque required to stir the material to be detected at the detection stirring speed.

[0008] Optionally, the training sample is constructed in the following manner: During the process of stirring the Newtonian fluid material by the test stirring device, collecting test stirring speed, test stirring torque and test viscosity data; The training samples are constructed based on the test stirring rotation speed, the test stirring torque and the test viscosity data.

[0009] Optionally, the target apparent viscosity detection model is trained in the following manner: Constructing an initial apparent viscosity detection model; Inputting the test stirring speed and the test stirring torque into the initial apparent viscosity detection model for prediction to obtain predicted viscosity data; The initial apparent viscosity detection model is updated based on the predicted viscosity data and the tested viscosity data until a model training stop condition is reached to obtain the target apparent viscosity detection model.

[0010] Optionally, the test stirring torque is obtained by: Obtaining the no-load torque of the test stirring device at the test stirring speed; wherein the no-load torque is the torque when there is no material in the test stirring device; Obtaining the load torque collected when the Newtonian fluid material is stirred at the test stirring speed; The difference between the load torque and the no-load torque is taken as the test stirring torque.

[0011] In a second aspect, an embodiment of the present application provides a device for detecting the apparent viscosity of a material, the device comprising: A model determination module, used to determine a target apparent viscosity detection model corresponding to a current stirring device; wherein the training sample of the target apparent viscosity detection model is constructed based on test data collected during the process of stirring a Newtonian fluid material with a test stirring device; the test stirring device and the current stirring device have the same device parameters; A speed and torque acquisition module, used to acquire the detection stirring speed and detection stirring torque of the material to be detected in the current stirring device; wherein the material to be detected is a Newtonian fluid material or a non-Newtonian fluid material; The speed and torque input module is used to input the detected stirring speed and the detected stirring torque into the target apparent viscosity detection model for inference to obtain the apparent viscosity of the material to be detected.

[0012] In a third aspect, an embodiment of the present application provides a computer device, including: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method described in any of the above embodiments by executing the computer instructions.

[0013] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable a computer to execute the method described in any of the above embodiments.

[0014] In the embodiment of the present application, the target apparent viscosity detection model corresponding to the current stirring device is first determined, and the training samples of the model are constructed based on the test data collected during the stirring of Newtonian fluid materials by the test stirring device, and the test stirring device has the same equipment parameters as the current stirring device. Then the detection stirring speed and the detection stirring torque of the material to be detected in the current stirring device are obtained, and the material to be detected can be a Newtonian fluid material or a non-Newtonian fluid material. Finally, the detection stirring speed and the detection stirring torque are input into the target apparent viscosity detection model for reasoning to obtain the apparent viscosity of the material to be detected. The training samples of the initial apparent viscosity detection model are constructed based on the test data collected during the stirring of Newtonian fluid materials by the test stirring device, which can ensure the accuracy and reliability of the training samples, thereby improving the reasoning accuracy of the model. And the target apparent viscosity detection model has a wide range of applicability, which can not only predict the apparent viscosity of Newtonian fluid materials, but also predict the apparent viscosity of non-Newtonian fluid materials. More importantly, this method does not require invasive sampling, can avoid interference with the flow field in the stirring device, realizes the in-situ online detection of the apparent viscosity of the material, and can reflect the overall apparent viscosity of the material in the stirring device in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 A flow chart of a method for detecting the apparent viscosity of a material provided in an embodiment of this specification; Figure 2 A flow chart of a method for detecting the apparent viscosity of a material provided in an embodiment of this specification; Figure 3 A schematic diagram of a stirred tank provided in an embodiment of this specification; Figure 4 A flow chart of a method for detecting the apparent viscosity of a material provided in an embodiment of this specification; Figure 5a A flow chart of a method for detecting the apparent viscosity of a material provided in an embodiment of this specification; Figure 5b A schematic diagram of the initial apparent viscosity detection model provided in the embodiments of this specification; Figure 6 A flow chart of a method for detecting the apparent viscosity of a material provided in an embodiment of this specification; Figure 7 A schematic diagram of a material apparent viscosity detection device provided in an embodiment of this specification; Figure 8 A schematic diagram of a computer structure provided in an embodiment of this specification. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0018] The detection of the apparent viscosity of materials is very critical in the chemical production process. Under actual working conditions, many chemical reactions are often accompanied by the change of the phase of the material, such as the change from liquid to solid particle precipitation, which causes a significant change in its apparent viscosity, from Newtonian fluid to non-Newtonian fluid. The apparent viscosity of non-Newtonian fluid will change with the change of shear rate, resulting in challenges in accurately obtaining its apparent viscosity. In related technologies, online viscometers such as vibration, rotation and optical types are used to monitor the change of fluid viscosity in real time, but online viscometers can only be detected at local points and cannot reflect the overall apparent viscosity of the material in the mixing equipment.

[0019] Based on this, the present application proposes a method for detecting the apparent viscosity of a material, the method comprising: first, determining a target apparent viscosity detection model corresponding to the current stirring device; wherein the training sample of the target apparent viscosity detection model is constructed based on the test data collected during the process of stirring a Newtonian fluid material in the test stirring device; the test stirring device has the same equipment parameters as the current stirring device; secondly, obtaining the detection stirring speed and detection stirring torque of the material to be detected in the current stirring device; wherein the material to be detected is a Newtonian fluid material or a non-Newtonian fluid material; finally, inputting the detection stirring speed and detection stirring torque into the target apparent viscosity detection model for inference to obtain the apparent viscosity of the material to be detected. The method calculates the apparent viscosity of the material based on the detection stirring speed and detection stirring torque of the material to be detected, does not require invasive sampling, can avoid interference with the flow field in the stirring device, realizes in-situ online detection of the apparent viscosity of the material, and can reflect the overall apparent viscosity of the material in the stirring device in real time. It effectively solves the problem in related technologies that sample consistency changes during offline detection, or that only local detection can be performed during online detection, resulting in inaccurate detection results. It can be applied to multiphase system occasions such as biological fermentation, polymerization reaction and emulsion preparation.

[0020] According to an embodiment of the present application, an embodiment of a method for detecting the apparent viscosity of a material is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0021] See also Figure 1 In this embodiment, a method for detecting the apparent viscosity of a material is provided, the method comprising: S110, determining a target apparent viscosity detection model corresponding to the current stirring device.

[0022] The current stirring device may be a container-type mechanical device for mixing and stirring liquid materials. The training samples of the target apparent viscosity detection model are constructed based on the test data collected during the process of stirring Newtonian fluid materials by the test stirring device; the test stirring device and the current stirring device have the same device parameters. The device parameters may include the shape, size, and stirrer type of the stirring device.

[0023] It should be noted that the apparent viscosity of Newtonian fluids is constant when subjected to external stress, and the characteristics are stable at different stirring speeds, making it easy to obtain accurate test data. However, the apparent viscosity of non-Newtonian fluids changes with stress or stirring speed, making it difficult to obtain accurate test data. Therefore, Newtonian fluid materials are used for testing and test data collection.

[0024] In some embodiments, test data is collected by stirring a Newtonian fluid material in a test stirring device, and then a sample set is constructed based on a large amount of test data to train the initial apparent viscosity detection model, thereby obtaining a target apparent viscosity detection model. It should be noted that, since there is a corresponding relationship between the test data and the equipment parameters of the test stirring device, the target apparent viscosity detection model is trained based on the test data of specific equipment parameters and is applicable to the current stirring device with the same equipment parameters.

[0025] In some embodiments, by stirring Newtonian fluid materials in test stirring devices with different equipment parameters, collecting test data corresponding to each equipment parameter, and then training the initial apparent viscosity detection model based on the sample set consisting of a large amount of test data corresponding to each equipment parameter, multiple target apparent viscosity detection models corresponding to each equipment parameter can be obtained. Exemplarily, a chemical enterprise has two stirring devices with equipment parameters A and B, respectively. An A equipment parameter test stirring device and a B equipment parameter test stirring device are selected. First, Newtonian fluid materials are added to the two test stirring devices for stirring, and a large amount of test data is collected to construct A training samples and B training samples; then, the initial apparent viscosity detection model is trained based on the A training sample to obtain the A target apparent viscosity detection model corresponding to the A equipment parameter. The A target apparent viscosity detection model is used to describe the corresponding relationship between the stirring speed, stirring torque and apparent viscosity when the material corresponding to the A equipment parameter is stirred. Similarly, the initial apparent viscosity detection model is trained based on the B training sample to obtain the B target apparent viscosity detection model corresponding to the B equipment parameter. B target apparent viscosity detection model is used to describe the corresponding relationship between the stirring speed, stirring torque and apparent viscosity of the material when the material is stirred corresponding to the B equipment parameter. Similarly, the corresponding target apparent viscosity detection model can be constructed based on a variety of different equipment parameters, and these different target apparent viscosity detection models can be constructed into a target apparent viscosity detection model set. Finally, in the production process, the equipment parameters of the current stirring equipment can be obtained first, and then the corresponding target apparent viscosity detection model can be selected from the constructed target apparent viscosity detection model set according to the equipment parameters to detect the material apparent viscosity, thereby achieving more accurate apparent viscosity control.

[0026] S120, obtaining the detection stirring speed and detection stirring torque of the material to be detected in the current stirring equipment.

[0027] Wherein, the material to be detected is a Newtonian fluid material or a non-Newtonian fluid material. The detected stirring speed may be the speed of stirring the material to be detected. The detected stirring torque may be the torque required to stir the material to be detected at the detected stirring speed.

[0028] In some embodiments, the material to be detected in the current stirring device is stirred by a stirrer, and a torque sensor and a rotation speed sensor may be installed on the stirrer to obtain the stirring rotation speed and the stirring torque.

[0029] In some embodiments, the torque sensor and the speed sensor need to be calibrated before use to ensure their accuracy. For example, the torque sensor and the speed sensor are installed on the stirring shaft of the stirred tank, and the electrical wiring needs to be checked first to ensure that the signal can be transmitted normally. Then, the two sensors are calibrated separately.

[0030] The calibration process of the torque sensor can be: use a dynamic torque calibrator to apply a known load torque to the stirring shaft, and compare the torque value output by the torque sensor with the standard torque value. Calibrate through multiple torque points of different sizes to fit the calibration curve of the torque sensor. According to the calibration results, adjust the zero point and gain coefficient of the torque sensor to ensure that its output value accurately matches the actual torque value. For example, in the range of 0 to 5N·m, at intervals of 0.5N·m, use a dynamic torque calibrator to apply load torque to the stirring shaft in turn, compare the output value of the torque sensor with the standard torque value, fit the calibration curve of the torque sensor through multi-point calibration, and adjust the zero point and gain coefficient of the torque sensor according to the calibration results.

[0031] The calibration process of the speed sensor can be: using a standard tachometer to accurately measure the actual speed of the stirring shaft, and comparing the speed value output by the speed sensor with the standard speed value. Calibrate through multiple different speed points to fit the calibration curve of the speed sensor. According to the calibration results, adjust the zero point and gain coefficient of the speed sensor so that its output value is highly consistent with the actual speed value. Exemplarily, within the range of 0 to 500rpm, at an interval of 25rpm, use a standard tachometer to measure the actual speed of the stirring shaft, compare the output value of the speed sensor with the standard speed value, fit the calibration curve of the speed sensor through multi-point calibration, and adjust the zero point and gain coefficient of the speed sensor according to the calibration results.

[0032] In some embodiments, first, the detected load torque and the detected stirring speed of the material to be detected in the current stirring device are obtained by a torque sensor and a speed sensor, respectively. Then, the detected load torque is subtracted from the detected no-load torque to obtain the detected stirring torque of the material to be detected. The detected no-load torque is the torque corresponding to the stirring of the material in the current stirring device when the material is emptied and the stirrer stirs at the detected stirring speed.

[0033] S130, inputting the detected stirring speed and the detected stirring torque into the target apparent viscosity detection model for inference to obtain the apparent viscosity of the material to be detected.

[0034] In some embodiments, the detected stirring speed and detected stirring torque of the Newtonian fluid material in the current stirring device are first obtained, and then input into the target apparent viscosity detection model for inference to obtain the apparent viscosity of the Newtonian fluid material.

[0035] In some embodiments, the detected stirring speed and detected stirring torque of the non-Newtonian fluid material in the current stirring device are first obtained, and then input into the target apparent viscosity detection model for inference to obtain the apparent viscosity of the non-Newtonian fluid material.

[0036] It should be noted that the training sample data needs to be obtained based on experiments. The apparent viscosity of non-Newtonian fluids is difficult to obtain directly based on experimental means, while the apparent viscosity of Newtonian fluids is easy to obtain. Therefore, the present invention is based on the stirring experiment of Newtonian fluids, obtains test stirring speed, test stirring torque and test viscosity data, and constructs a training sample set. Further, the apparent viscosity of a material has nothing to do with whether the material belongs to a Newtonian fluid or a non-Newtonian fluid. It should be emphasized that, after analysis by the inventor, for stirring equipment with the same equipment parameters and fluids with the same apparent viscosity, the required stirring torque is the same at the same stirring speed. Therefore, based on the training sample set constructed by Newtonian fluids, the target apparent viscosity detection model obtained after training can infer the apparent viscosity of Newtonian fluid materials and the apparent viscosity of non-Newtonian fluid materials. The fundamental reason is that the model has learned the intrinsic relationship between the test stirring torque, the test stirring speed and the test viscosity data. As long as this relationship is the same, the model can use the learned pattern to predict the apparent viscosity of the material.

[0037] In the above embodiment, the target apparent viscosity detection model corresponding to the current stirring device is first determined, and the training samples of the model are constructed based on the test data collected during the process of stirring Newtonian fluid materials in the test stirring device, and the test stirring device has the same equipment parameters as the current stirring device. Then, the detection stirring speed and the detection stirring torque of the material to be detected in the current stirring device are obtained, and the material to be detected can be a Newtonian fluid material or a non-Newtonian fluid material. Finally, the detection stirring speed and the detection stirring torque are input into the target apparent viscosity detection model for reasoning to obtain the apparent viscosity of the material to be detected. The training samples of the initial apparent viscosity detection model are constructed based on the test data collected during the process of stirring Newtonian fluid materials in the test stirring device, which can ensure the accuracy and reliability of the training samples, thereby improving the reasoning accuracy of the model. And the model has a wide range of applicability, and can not only predict the apparent viscosity of Newtonian fluid materials, but also predict the apparent viscosity of non-Newtonian fluid materials. More importantly, this method does not require invasive sampling, realizes the in-situ online detection of the apparent viscosity of the material, can reflect the overall apparent viscosity of the material in the stirring device in real time, and can avoid interference with the flow field in the stirring device.

[0038] See also Figure 2 In some embodiments, determining a target apparent viscosity detection model corresponding to the current stirring device includes: S210, obtaining the target device type of the current mixing device; S220: Determine the apparent viscosity detection model corresponding to the target device type as the target apparent viscosity detection model.

[0039] The target device type may be the brand or model information of the current stirring device or a combination of the two. The current stirring devices of the same target device type have the same shape, size, stirrer type, and the like.

[0040] Specifically, the target apparent viscosity detection model and the target equipment type have a one-to-one correspondence. Different target equipment types of stirring equipment require different target apparent viscosity detection models to describe the nonlinear relationship between different detection stirring torques, detection stirring speeds and material viscosity. Therefore, in order to improve the accuracy of model prediction, it is necessary to train the initial apparent viscosity detection model for each current stirring equipment of each target equipment type.

[0041] In some embodiments, the detected stirring torque and the detected stirring speed of the material to be detected are first collected, and then the target device type of the current stirring device is obtained, and then the corresponding target apparent viscosity detection model is determined according to the target device type, and finally the detected stirring torque and the detected stirring speed are input into the target apparent viscosity detection model for reasoning to obtain the apparent viscosity of the material to be detected.

[0042] In the above embodiment, based on the target device type of the current stirring device, a target apparent viscosity detection model is determined for inference, which helps to improve the accuracy of the apparent viscosity inference of the material to be detected.

[0043] In some embodiments, the liquid level of the material to be detected in the current stirring device reaches a preset height; obtaining the detection stirring speed and the detection stirring torque of the material to be detected in the current stirring device includes: When the liquid level of the material to be detected reaches a preset height, the detection stirring speed and the detection stirring torque are obtained.

[0044] Among them, the preset liquid level height of the current stirring equipment can be a plurality of liquid level heights commonly used in production, for example, 150mm, 200mm, 250mm, 300mm, etc.

[0045] Specifically, for the materials to be tested with the same apparent viscosity, when the same detection stirring speed is used for stirring, the liquid level height will have a certain influence on the required detection stirring torque. It should be noted that in the actual production process, it is found that sometimes there is a large error in the reasoning of the apparent viscosity of the material. After in-depth analysis, it is found that the reason for this problem is that the liquid level height of the material in the stirring equipment is different. Therefore, in order to further improve the accuracy of the apparent viscosity reasoning, the liquid level height condition is taken into consideration. Based on this, there is a one-to-one correspondence between the target apparent viscosity detection model and the target equipment type, as well as the liquid level height. Different combinations of target equipment types and liquid level heights require different target apparent viscosity detection models to describe different detection stirring torques, detection stirring speeds and nonlinear relationships between material viscosity. In order to improve the accuracy of model prediction, it is necessary to train the initial apparent viscosity detection model separately for each target equipment type and liquid level height combination. For example, a chemical company has two stirring equipments with target equipment types A and B, respectively, and there are two preset liquid level heights: h1 and h2. Select two A target equipment type test stirring equipment. First, add Newtonian fluid materials to the two test stirring equipment respectively. The liquid level in the first A target equipment type test stirring equipment is h1, and the liquid level in the second A target equipment type test stirring equipment is h2. Then stir, collect a large amount of test data, and construct Ah1 training samples and Ah2 training samples. Then, the initial apparent viscosity detection model is trained based on the Ah1 training sample to obtain the Ah1 target apparent viscosity detection model corresponding to the A target equipment type and the h1 liquid level height. The Ah1 target apparent viscosity detection model is used to describe the corresponding relationship between the stirring speed, stirring torque and apparent viscosity when the material is stirred corresponding to the A target equipment type and the h1 liquid level height. Similarly, the initial apparent viscosity detection model is trained based on the Ah2 training sample to obtain the Ah2 target apparent viscosity detection model corresponding to the A target equipment type and the h2 liquid level height. The Ah2 target apparent viscosity detection model is used to describe the corresponding relationship between the stirring speed, stirring torque and apparent viscosity when the material is stirred corresponding to the A target equipment type and the h2 liquid level height. Similarly, corresponding target apparent viscosity detection models can be constructed based on a variety of different target equipment types and liquid level heights. These different target apparent viscosity detection models can be constructed into a target apparent viscosity detection model set. The target apparent viscosity detection model corresponding to each target equipment type belongs to a subset of the target apparent viscosity detection model set. Finally, in the production process, the target equipment type of the current stirring equipment can be obtained first, and then the corresponding target apparent viscosity detection model can be selected from the constructed target apparent viscosity detection model set according to the liquid level height to detect the material apparent viscosity, thereby achieving more accurate apparent viscosity control.

[0046] In some embodiments, the material to be detected is first added to the current stirring device to a preset height, and then the stirring device is started for stirring, and the detected stirring torque and detected stirring speed of the material to be detected are collected, and then the target device type of the current stirring device is obtained, and then according to the target device type and the preset height, the corresponding target apparent viscosity detection model is determined, and finally the detected stirring torque and detected stirring speed are input into the target apparent viscosity detection model for reasoning to obtain the apparent viscosity of the material to be detected.

[0047] In the above embodiment, taking into account the influence of liquid level height on the detection of stirring torque, the detection of the nonlinear relationship between stirring speed and material viscosity, determining the target apparent viscosity detection model based on the target equipment type and liquid level height helps to further improve the accuracy of the apparent viscosity reasoning of the material to be detected.

[0048] In some embodiments, the current stirring device is configured with a motor and an agitator; the motor is used to drive the agitator to stir the material to be detected so that the material to be detected is in a laminar flow state; the detected stirring speed is the speed of the material to be detected in the laminar flow state; the detected stirring torque is the torque required to stir the material to be detected at the detected stirring speed.

[0049] Among them, the laminar state can be a flow state of the fluid, in which the various parts of the fluid flow in layers and do not mix with each other. It usually occurs when the stirring Reynolds number (Re) is small, that is, when the stirring speed is detected to be low. As the stirring speed increases, the Reynolds number increases, and the fluid will enter a turbulent state. Therefore, in the laminar state, the detection of the stirring torque can reflect the flow resistance encountered by the agitator during the rotation process, and the magnitude of the flow resistance is closely related to the apparent viscosity of the material. The detection of the stirring torque is jointly affected by the detection stirring speed, the apparent viscosity of the material and the type of agitator, and there is a nonlinear mapping relationship between them. When the material to be detected is in a turbulent state, this nonlinear relationship will not hold.

[0050] In some embodiments, see Figure 3 The current stirring device is a multiphase stirring kettle, the control cabinet 401 is connected to the motor 402, the torque sensor 403 and the speed sensor 404 are installed on the stirring shaft 405, and the output value is transmitted to the control cabinet 401, the upper end of the stirring shaft 405 is connected to the motor 402, and the lower end is installed with a stirrer 406. Specifically, the speed of the motor 402 can be adjusted by the control cabinet 401, and the stirrer 406 can be driven at a lower speed (for example, lower than 90rpm) to stir the material to be detected, so that the material to be detected is in a laminar state.

[0051] In some embodiments, when the material to be detected is in a laminar flow state, the detection stirring torque is jointly affected by the detection stirring speed, the apparent viscosity of the material, the type of agitator, and the liquid level of the material to be detected, forming a nonlinear relationship. Therefore, when training the initial apparent viscosity detection model, the test data needs to be collected when the Newtonian fluid material is in a laminar flow state. Accordingly, when predicting the apparent viscosity of the material to be detected, it is also necessary to control the detection stirring speed so that the material to be detected is in a laminar flow state, thereby obtaining an accurate apparent viscosity value.

[0052] See also Figure 4 In some embodiments, the training samples are constructed in the following manner: S510, in the process of testing the stirring device stirring the Newtonian fluid material, collecting the test stirring speed, the test stirring torque and the test viscosity data; S520: construct training samples based on the test stirring speed, the test stirring torque and the test viscosity data.

[0053] Among them, the test stirring speed can be the speed data of the stirrer obtained by the speed sensor during the process of the stirring device stirring the Newtonian fluid material. The test stirring torque can be the torque data of the stirrer obtained by the torque sensor during the process of the stirring device stirring the Newtonian fluid material. The test viscosity data can be the viscosity data of the stirred Newtonian fluid material, which can be measured and obtained by a rotor viscometer. It should be noted that during the stirring process, it is necessary to ensure that the Newtonian fluid material is in a laminar state.

[0054] In some embodiments, when the stirring Reynolds number of a stirring device in an industrial production environment is less than 100, the material therein may be in a laminar flow state. According to the Reynolds number formula: (Where Re is the stirring Reynolds number, is the density of the material, D is the diameter of the agitator blade, is the test viscosity data of the material, N is the test stirring speed), the test stirring speed threshold that makes the Newtonian fluid material in a laminar state can be calculated. For example, the total volume of the stirred tank is 10L, the type of the stirrer is a six-straight blade disc turbine, the blade diameter is D=0.15m, and the test viscosity data of maltose syrup water is =0.5Pa·s, density is =1450kg / m3. According to the Reynolds number formula, it can be calculated that the test stirring speed must be controlled below 90rpm to make the material in the stirring tank in a laminar state.

[0055] In some embodiments, a Newtonian fluid material is selected for stirring test to construct a training sample. Exemplarily, a maltose syrup aqueous solution is selected as a Newtonian fluid material, and a plurality of solutions with different apparent viscosities are prepared by adjusting the ratio of water and maltose syrup. Exemplarily, maltose syrup aqueous solutions with different apparent viscosities such as 0.5Pa·s, 1Pa·s, 1.5Pa·s, 2Pa·s, 2.5Pa·s and 3Pa·s are prepared, and these different apparent viscosities are test viscosity data.

[0056] Furthermore, a torque sensor and a speed sensor are installed on the stirring shaft of the test stirring device, ensuring that the sensor installation position is accurate, the electrical wiring is not interfered with, and calibration is performed. When the material in the stirring tank is emptied, the stirrer is started and the stirring speed is adjusted to different values ​​(for example, from 0 to 90 rpm, with an interval of 5 rpm) as the test stirring speed, and the no-load torque at each test stirring speed is recorded.

[0057] Furthermore, a maltose syrup aqueous solution with a test viscosity data of 0.5Pa·s is added to the test stirring device, and the liquid level is set to 300mm. Start the agitator, adjust the stirring speed to each test stirring speed at no-load in turn, and record the test load torque at each test stirring speed. Subtract the corresponding no-load torque from the test load torque at each test stirring speed to obtain the test stirring torque. At this point, the test stirring speed and test stirring torque of the test stirring device are obtained when the liquid level is 300mm and the test viscosity data is 0.5Pa·s. In the above manner, the test stirring speed and test stirring torque when the test viscosity data are 1Pa·s, 1.5Pa·s, 2Pa·s, 2.5Pa·s and 3Pa·s can also be collected.

[0058] Finally, based on the collected test stirring speed, test stirring torque and test viscosity data, normalization is performed, and then training samples are constructed to train the initial apparent viscosity detection model, and a target apparent viscosity detection model corresponding to the target device type and liquid level height of 300 mm of the test stirring device can be obtained. It should be noted that the liquid level height can also be set to other liquid level height values ​​commonly used in industrial production, and then training samples are constructed in the above manner to obtain a target apparent viscosity detection model corresponding to the target device type and liquid level height.

[0059] In the above embodiment, accurate test data is obtained by testing Newtonian fluid materials, which provides a reliable basis for model training, helps the model learn the accurate relationship between test stirring torque, test stirring speed and test viscosity data during the training process, and improves the reasoning accuracy of the target apparent viscosity detection model.

[0060] See also Figure 5aIn some embodiments, the target apparent viscosity detection model is trained in the following manner: S610, constructing an initial apparent viscosity detection model.

[0061] S620, input the test stirring speed and the test stirring torque into the initial apparent viscosity detection model for prediction to obtain predicted viscosity data.

[0062] S630, updating the initial apparent viscosity detection model based on the predicted viscosity data and the test viscosity data until the model training stop condition is reached, thereby obtaining a target apparent viscosity detection model.

[0063] In some embodiments, a back propagation neural network (BPNN) is selected as the initial apparent viscosity detection model, see Figure 5b , the input layer includes two parameters: test stirring speed and test stirring torque, the hidden layer uses 5 neurons, and the output layer is 1 parameter: predicted viscosity data. It should be noted that other models that support nonlinear relationship mapping can also be selected as the initial apparent viscosity detection model.

[0064] In some embodiments, first, the training samples are randomly sampled and divided into a training set, a validation set, and a test set according to the ratio of 70%, 15%, and 15%. The training set is used for the preliminary training of the initial apparent viscosity detection model, the validation set is used to adjust the hyperparameters of the intermediate apparent viscosity detection model to prevent overfitting, and the test set is used to finally evaluate the performance and generalization ability of the target apparent viscosity detection model.

[0065] In some embodiments, first, the test stirring speed and the test stirring torque in the training set are input into the initial apparent viscosity detection model, and forward propagation is performed to obtain predicted viscosity data. Then, the error between the predicted viscosity data and the test viscosity data is calculated. Next, the weight and bias parameters of the model are adjusted using a back propagation algorithm to minimize the error. The above training process is repeated until the model reaches a preset stop condition to obtain an intermediate apparent viscosity detection model.

[0066] In some embodiments, the hyperparameters of the intermediate apparent viscosity detection model are first adjusted through the validation set to prevent overfitting, and then the inference error of the intermediate apparent viscosity detection model is evaluated through the test set. Exemplarily, if the errors are all within 10%, the intermediate apparent viscosity detection model is determined to be the target apparent viscosity detection model.

[0067] In the above embodiment, based on the constructed initial apparent viscosity detection model, the model is trained by using test data to finally obtain a target apparent viscosity detection model, which can accurately predict the apparent viscosity of the material and provide a reliable means for real-time monitoring of the apparent viscosity of the material in the stirring equipment.

[0068] See also Figure 6 In some embodiments, the test stirring torque is obtained by: S710, obtaining the no-load torque of the test stirring device when the stirring speed is tested.

[0069] S720: Obtain the load torque collected when the Newtonian fluid material is stirred at a test stirring speed.

[0070] S730: The difference between the load torque and the no-load torque is used as the test stirring torque.

[0071] The no-load torque is the torque when there is no material in the testing mixing equipment.

[0072] In some embodiments, the test stirring device is a stirring kettle, and a calibrated torque sensor and a speed sensor are installed on the stirring shaft of the stirring kettle to measure the torque and speed. First, the material in the stirring kettle is emptied, and the motor is adjusted to drive the stirring shaft at a certain speed (less than 100 rpm) for stirring, and then the speed and the corresponding output value of the torque sensor are recorded, which is a set of test stirring speed and no-load torque data. It should be noted that when collecting test data, multiple sets of data can be recorded in the above manner.

[0073] Further, a Newtonian fluid material with known apparent viscosity is added to the stirring kettle, and then the motor is adjusted to stir the Newtonian fluid material at a certain test stirring speed when the stirring kettle is unloaded, and the output value of the torque sensor, i.e., the load torque, is recorded. Exemplarily, other recorded test stirring speeds can be switched to stir the Newtonian fluid material to obtain the load torque at different test stirring speeds.

[0074] Furthermore, by calculating the difference between the load torque and the no-load torque in each set of recorded data, the test stirring torque is obtained, thereby obtaining multiple sets of test data of the test viscosity data, the test stirring speed and the test stirring torque.

[0075] In the above embodiment, accurate test data is obtained by testing Newtonian fluid materials, which provides a reliable basis for model training, helps the model learn the accurate relationship between test stirring torque, test stirring speed and test viscosity data during the training process, and improves the reasoning accuracy of the target apparent viscosity detection model.

[0076] See also Figure 7In this embodiment, a device 800 for detecting the apparent viscosity of a material is provided. The device 800 for detecting the apparent viscosity of a material comprises: The model determination module 810 is used to determine the target apparent viscosity detection model corresponding to the current stirring device; wherein the training sample of the target apparent viscosity detection model is constructed based on the test data collected during the process of stirring the Newtonian fluid material by the test stirring device; the test stirring device and the current stirring device have the same device parameters; The speed and torque acquisition module 820 is used to acquire the detection stirring speed and detection stirring torque of the material to be detected in the current stirring device; wherein the material to be detected is a Newtonian fluid material or a non-Newtonian fluid material; The speed and torque input module 830 is used to input the detected stirring speed and the detected stirring torque into the target apparent viscosity detection model for inference to obtain the apparent viscosity of the material to be detected.

[0077] In some implementations, the model determination module 810 further includes: A target device type acquisition unit, used to acquire the target device type of the current mixing device; The model determination unit is used to determine the apparent viscosity detection model corresponding to the target device type as the target apparent viscosity detection model.

[0078] In some embodiments, the liquid level of the material to be detected in the current stirring device reaches a preset height; the speed torque acquisition module 820 further includes: The speed and torque acquisition unit is used to acquire the detection stirring speed and the detection stirring torque when the liquid level of the material to be detected reaches a preset height.

[0079] In some embodiments, the current stirring device is configured with a motor and an agitator; the motor is used to drive the agitator to stir the material to be tested so that the material to be tested is in a laminar state; the material apparent viscosity detection device 800 also needs to determine that the detected stirring speed is the speed of the material to be tested in a laminar state; and determine that the detected stirring torque is the torque required to stir the material to be tested at the detected stirring speed.

[0080] In some embodiments, the device 800 for detecting the apparent viscosity of a material further includes a training sample construction module, and the training sample construction module further includes: A test data acquisition unit, used to collect test stirring speed, test stirring torque and test viscosity data during the process of stirring Newtonian fluid materials by the test stirring device; The training sample construction unit is used to construct training samples based on test stirring speed, test stirring torque and test viscosity data.

[0081] In some embodiments, the device 800 for detecting the apparent viscosity of a material further includes a model training module, and the model training module further includes: A model building unit, used for building an initial apparent viscosity detection model; A prediction data acquisition unit, used for inputting the test stirring speed and the test stirring torque into the initial apparent viscosity detection model for prediction, to obtain predicted viscosity data; The model updating unit is used to update the initial apparent viscosity detection model based on the predicted viscosity data and the tested viscosity data until the model training stop condition is reached to obtain the target apparent viscosity detection model.

[0082] In some embodiments, the device 800 for detecting the apparent viscosity of a material further includes a testing stirring torque acquisition module, and the testing stirring torque acquisition module further includes: A no-load torque acquisition unit is used to acquire the no-load torque of the test stirring device when the stirring speed is tested; wherein the no-load torque is the torque when there is no material in the test stirring device; A load torque acquisition unit, used to acquire the load torque collected when the Newtonian fluid material is stirred at a test stirring speed; The test stirring torque determination module is used to use the difference between the load torque and the no-load torque as the test stirring torque.

[0083] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0084] The device for detecting the apparent viscosity of the material in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0085] See also Figure 8 , Figure 8 is a schematic diagram of the structure of a computer device provided in an embodiment of the present application, such as Figure 8As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 8 A processor 10 is taken as an example.

[0086] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0087] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0088] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0089] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0090] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 8 The example of connecting through bus is taken in the following.

[0091] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device may be a touch screen.

[0092] The embodiment of the present application also provides a computer-readable storage medium. The above method according to the embodiment of the present application can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or is implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0093] The embodiment of the present application provides a computer program product, which includes computer instructions, which are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method of any embodiment of the present application.

[0094] Although the embodiments of the present application are described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

[0095] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0096] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0097] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0098] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0099] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0100] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0101] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0102] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0103] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

[0104] Although the embodiments of the present application have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for detecting the apparent viscosity of a material, characterized in that: The method comprises: Determine a target apparent viscosity detection model corresponding to the current stirring device; wherein the training sample of the target apparent viscosity detection model is constructed based on test data collected during the process of stirring a Newtonian fluid material with the test stirring device; the test stirring device and the current stirring device have the same device parameters; Acquire the detection stirring speed and detection stirring torque of the material to be detected in the current stirring device; wherein the material to be detected is a Newtonian fluid material or a non-Newtonian fluid material; The detected stirring speed and the detected stirring torque are input into the target apparent viscosity detection model for inference to obtain the apparent viscosity of the material to be detected.

2. The method according to claim 1, characterized in that The step of determining a target apparent viscosity detection model corresponding to the current stirring device includes: Obtaining the target device type of the current mixing device; The apparent viscosity detection model corresponding to the target device type is determined as the target apparent viscosity detection model.

3. The method according to claim 2, characterized in that The liquid level of the material to be detected in the current stirring device reaches a preset height; and obtaining the detected stirring speed and the detected stirring torque of the material to be detected in the current stirring device includes: When the liquid level of the material to be detected reaches the preset height, the detected stirring speed and the detected stirring torque are obtained.

4. The method according to claim 1, characterized in that: The current stirring device is configured with a motor and a stirrer; the motor is used to drive the stirrer to stir the material to be detected so that the material to be detected is in a laminar flow state; The detection stirring speed is the speed of the material to be detected in a laminar flow state; The detection stirring torque is the torque required to stir the material to be detected at the detection stirring speed.

5. The method according to claim 1, characterized in that The training samples are constructed in the following way: During the process of stirring the Newtonian fluid material by the test stirring device, collecting test stirring speed, test stirring torque and test viscosity data; The training samples are constructed based on the test stirring rotation speed, the test stirring torque and the test viscosity data.

6. The method according to claim 5, characterized in that The target apparent viscosity detection model is trained in the following way: Constructing an initial apparent viscosity detection model; Inputting the test stirring speed and the test stirring torque into the initial apparent viscosity detection model for prediction to obtain predicted viscosity data; The initial apparent viscosity detection model is updated based on the predicted viscosity data and the tested viscosity data until a model training stop condition is reached to obtain the target apparent viscosity detection model.

7. The method according to claim 5, characterized in that The test stirring torque is obtained by: Obtaining the no-load torque of the test stirring device at the test stirring speed; wherein the no-load torque is the torque when there is no material in the test stirring device; Obtaining the load torque collected when the Newtonian fluid material is stirred at the test stirring speed; The difference between the load torque and the no-load torque is taken as the test stirring torque.

8. A device for detecting the apparent viscosity of a material, characterized in that: The device comprises: A model determination module, used to determine a target apparent viscosity detection model corresponding to a current stirring device; wherein the training sample of the target apparent viscosity detection model is constructed based on test data collected during the process of stirring a Newtonian fluid material with a test stirring device; the test stirring device and the current stirring device have the same device parameters; A speed and torque acquisition module, used to acquire the detection stirring speed and detection stirring torque of the material to be detected in the current stirring device; wherein the material to be detected is a Newtonian fluid material or a non-Newtonian fluid material; The speed and torque input module is used to input the detected stirring speed and the detected stirring torque into the target apparent viscosity detection model for inference to obtain the apparent viscosity of the material to be detected.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

Images