Intelligent servo drive control method and system for nanometer homogenizer

Abstract

The invention provides an intelligent servo drive control method and system for a nano homogenizer, and the method comprises the steps: firstly obtaining vortex pressure values of the nano homogenizer in all directions, constructing a vortex pressure feature vector, determining a material vortex deviation direction and a material vortex deviation length through the vortex pressure feature vector, and then carrying out the servo drive control of the nano homogenizer. A servo controller is adopted to carry out primary servo control on the feeding gravity center of the homogenizing head; performing servo control detection based on the material delay particle size characteristics and the material eddy current offset length to obtain an eddy current control regulation factor of the homogenizing head; the control parameters of the servo controller are corrected on the basis of the eddy current control regulation factor of the homogenizing head, and the servo controller is adopted to carry out secondary servo control on the feeding gravity center of the homogenizing head, so that servo control can be carried out on the feeding gravity center of the homogenizing head according to the material eddy current deviation condition; therefore, the nano homogenizer does not need to be frequently shut down for inspection, and the working efficiency of the nano homogenizer is improved.

Description

Technical Field

[0001] The present application relates to the technical field of servo drive control, and more specifically, to an intelligent servo drive control method and system for a nano homogenizer. Background Art

[0002] A nano-homogenizer, also known as a high-pressure homogenizer, uses a high-pressure reciprocating pump as a power source to transmit and convey materials. It delivers liquid materials or solid particles in a liquid carrier to the working valve. "Homogenization" refers to the process of finely disintegrating and uniformly mixing the materials within the homogenizing valve. High-pressure homogenizers are specialized and key equipment for homogenizing, finely disintegrating, and conveying liquid materials at high pressure. The homogenization effect impacts product quality.

[0003] When the material passes through the narrow gap of the homogenizing head at a high speed, the eddy current generates a shear force on the fat, causing the fat to break. However, since the material can only produce a shearing effect when it generates a vortex eddy current, and whether the material can generate a vortex eddy current depends on whether the homogenizing rod must be concentric and equidistant from the homogenizing seat under the huge reaction force of the material. Once eccentricity occurs, the material will form a blowout instead of forming a vortex eddy current, and the shearing effect cannot be achieved. In the existing technology, whether the material produces a shearing effect is mainly inferred by repeated particle size detection. However, the particle size detection has a certain detection time and the system responsiveness is poor. In addition, if the particle size detection is abnormal, the nano homogenizer must be stopped and inspected, which greatly restricts the working efficiency of the nano homogenizer. Summary of the Invention

[0004] The present application provides an intelligent servo drive control method and system for a nano homogenizer, which can servo-control the feed center of gravity of the homogenizing head according to the eddy current deviation of the material, so that the nano homogenizer does not need to be frequently stopped for inspection, thereby improving the working efficiency of the nano homogenizer.

[0005] In a first aspect, the present application provides an intelligent servo drive control method for a nano-homogenizer. The method can be executed by a network device, or can also be executed by a chip configured in the network device, and the present application does not limit this.

[0006] Specifically, the method includes: Starting the nano homogenizer control to obtain the eddy current pressure value of the homogenizing head in each radial direction of the nano homogenizer; The eddy current pressure characteristic vector is constructed from the eddy current pressure values ​​in each direction, and the eddy current offset direction and the eddy current offset length of the material are determined by the eddy current pressure characteristic vector; Determining control parameters of a servo controller according to the material eddy current offset direction and the material eddy current offset length, and using the servo controller to perform a servo control on the feed center of gravity of the homogenizing head; Obtaining the delayed particle size characteristics of the material, performing servo control detection based on the delayed particle size characteristics of the material and the eddy current offset length of the material, and obtaining the eddy current control adjustment factor of the homogenizing head; The control parameters of the servo controller are corrected based on the eddy current control adjustment factor of the homogenizing head, and the servo controller is used to perform secondary servo control on the feeding center of gravity of the homogenizing head.

[0007] In conjunction with the first aspect, in certain implementations of the first aspect, determining control parameters of a servo controller based on the material eddy current offset direction and the material eddy current offset length, and using the servo controller to perform a servo control on the feed center of gravity of the homogenizing head specifically includes: Determining a target compensation angle range of the servo controller according to the material eddy current deviation direction; For all feed valves within the target compensation angle range, a compensation weight is determined based on the offset angle between the corresponding direction of each feed valve and the material vortex offset direction, and a control compensation amount corresponding to each feed valve connected to the servo controller is determined based on the material vortex offset length and the compensation weight; According to the control compensation amount and compensation weight corresponding to each feed valve, the opening of each feed valve is servo-controlled by the servo controller.

[0008] In combination with the first aspect, in certain implementations of the first aspect, correcting the control parameters of the servo controller based on the eddy current control adjustment factor of the homogenizing head specifically includes: Obtaining the particle size static control feature and the material eddy current dynamic feature in the eddy current control adjustment factor of the homogenizing head, and weightedly fusing the particle size static control feature and the material eddy current dynamic feature based on preset static weight coefficients and dynamic weight coefficients to obtain a servo correction coefficient; The integral adjustment coefficient of the servo controller is corrected according to the servo correction coefficient.

[0009] In combination with the first aspect, in certain implementations of the first aspect, the particle size of the material output by the homogenizing head is detected at equal intervals by a particle size detection device to obtain the material delayed particle size characteristics, which include multiple material detection particle sizes and their corresponding detection times.

[0010] In conjunction with the first aspect, in certain implementations of the first aspect, constructing an eddy pressure characteristic vector from eddy pressure values ​​in various directions, and determining the material eddy deviation direction and the material eddy deviation length using the eddy pressure characteristic vector specifically includes: Obtaining eddy current pressure values ​​in all directions to perform pressure dispersion detection, obtaining eddy current pressure dispersion corresponding to the eddy current pressure values, and normalizing the eddy current pressure values ​​in all directions according to the maximum eddy current pressure value; According to the normalized eddy pressure values ​​in each direction, eddy pressure characteristic vectors are constructed respectively, and the eddy pressure characteristic vectors corresponding to each direction are obtained; The eddy pressure characteristic vectors corresponding to each direction are vector-fused to obtain the material eddy current offset vector. The corresponding material eddy current offset direction and material eddy current offset length are determined according to the eddy current pressure dispersion corresponding to the eddy current pressure value and the material eddy current offset vector.

[0011] In combination with the first aspect, in certain implementations of the first aspect, in the process of obtaining the eddy current pressure values ​​of the homogenizing head in each radial direction in the nano-homogenizer, the pressure values ​​of the homogenizing head in each direction are collected in real time by an annular array pressure sensor as the eddy current pressure values ​​in each radial direction.

[0012] In combination with the first aspect, in certain implementations of the first aspect, performing servo control detection based on the delayed particle size characteristics of the material and the eddy current offset length of the material to obtain the eddy current control adjustment factor of the homogenizing head specifically includes: Obtaining each material detection particle size and its corresponding detection time in the material delayed particle size feature, performing particle size control trend extraction based on each material detection particle size and its corresponding detection time, obtaining a particle size control trend corresponding to the material detection particle size, and extracting a particle size static control feature based on the particle size control trend; Obtaining the eddy current offset length of each material and the time tag corresponding to each eddy current offset length of each material, performing time series fitting on the eddy current offset length of each material based on the time tag to obtain a material eddy current length model; Based on the material eddy length model, the particle size control trend is subjected to correlation feature learning to determine the particle size dynamic control feature, and the eddy control adjustment factor is composed of the particle size static control feature and the particle size dynamic control feature.

[0013] In a second aspect, the present application provides an intelligent servo drive control system for a nano-homogenizer, which includes a servo control unit, and the servo control unit includes: The eddy current pressure acquisition module is used to start the nano homogenizer control and obtain the eddy current pressure value of the homogenizing head in each radial direction of the nano homogenizer; The eddy current offset detection module constructs an eddy current pressure characteristic vector from the eddy current pressure values ​​in each direction, and determines the material eddy current offset direction and material eddy current offset length through the eddy current pressure characteristic vector; a first servo control module, configured to determine control parameters of a servo controller according to the material eddy current offset direction and the material eddy current offset length, and to perform a servo control on the feed center of gravity of the homogenizing head using the servo controller; A second servo control module is used to obtain the delayed particle size characteristics of the material, perform servo control detection based on the delayed particle size characteristics of the material and the eddy current offset length of the material, and obtain the eddy current control adjustment factor of the homogenizing head; The second servo control module is further configured to calibrate the control parameters of the servo controller based on the eddy current control adjustment factor of the homogenizing head, and to perform secondary servo control on the feed gravity center of the homogenizing head using the servo controller.

[0014] In a third aspect, the present application provides a computer terminal device, which includes a memory and a processor, wherein the memory stores a code, and the processor is configured to obtain the code and execute the above-mentioned intelligent servo drive control method for a nano homogenizer.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium, which stores at least one computer program, and the computer program is loaded and executed by a processor to implement the operations performed by the above-mentioned intelligent servo drive control method for a nano homogenizer.

[0016] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: The present application provides an intelligent servo drive control method and system for a nano homogenizer. First, the nano homogenizer control is started to obtain the eddy current pressure value of the homogenizing head in each radial direction of the nano homogenizer; the eddy current pressure characteristic vector is constructed from the eddy current pressure values ​​in each direction, and the material eddy current offset direction and the material eddy current offset length are determined by the eddy current pressure characteristic vector; the control parameters of the servo controller are determined according to the material eddy current offset direction and the material eddy current offset length, and the servo controller is used to perform a primary servo control on the feeding center of gravity of the homogenizing head; the material delayed particle size characteristics are obtained, and servo control detection is performed based on the material delayed particle size characteristics and the material eddy current offset length to obtain the eddy current control adjustment factor of the homogenizing head; the control parameters of the servo controller are corrected based on the eddy current control adjustment factor of the homogenizing head, and the servo controller is used to perform a secondary servo control on the feeding center of gravity of the homogenizing head.

[0017] It can be seen that the present application captures the changes in radial eddy pressure in real time, and determines the material eddy offset direction and material eddy offset length by constructing the eddy pressure characteristic vector. It can not only detect the pressure eccentricity and eccentricity direction of the homogenizing head in real time, but also servo-control the feed center of gravity of the homogenizing head according to the material eddy offset, so that the nano homogenizer does not need to be frequently shut down for inspection, thereby improving the working efficiency of the nano homogenizer. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is an exemplary flow chart of an intelligent servo drive control method for a nano-homogenizer according to some embodiments of the present application; Figure 2 is a schematic diagram of exemplary hardware and / or software of a servo control unit according to some embodiments of the present application; Figure 3 It is a structural schematic diagram of a computer terminal device for implementing an intelligent servo drive control method for a nano homogenizer according to some embodiments of the present application. DETAILED DESCRIPTION

[0019] The present application starts the nano homogenizer control to obtain the eddy current pressure value of the homogenizing head in each radial direction of the nano homogenizer; constructs the eddy current pressure characteristic vector from the eddy current pressure values ​​in each direction, and determines the material eddy current offset direction and the material eddy current offset length through the eddy current pressure characteristic vector; determines the control parameters of the servo controller according to the material eddy current offset direction and the material eddy current offset length, and uses the servo controller to perform a servo control on the feeding center of gravity of the homogenizing head; obtains the material delayed particle size characteristics, performs servo control detection based on the material delayed particle size characteristics and the material eddy current offset length, and obtains the eddy current control adjustment factor of the homogenizer; corrects the control parameters of the servo controller based on the eddy current control adjustment factor of the homogenizer, and uses the servo controller to perform secondary servo control on the feeding center of gravity of the homogenizer, which can perform servo control on the feeding center of gravity of the homogenizer according to the material eddy current offset situation, so that the nano homogenizer does not need to be frequently shut down for inspection, thereby improving the working efficiency of the nano homogenizer.

[0020] In order to better understand the above technical solution, the following will be combined with the accompanying drawings and specific implementation methods to describe the above technical solution in detail. Figure 1 , which is an exemplary flow chart of an intelligent servo drive control method for a nano homogenizer according to some embodiments of the present application. The intelligent servo drive control method 100 for a nano homogenizer mainly includes the following steps: In step S101, the nano-homogenizer control is started to obtain the eddy current pressure value of the homogenizing head in each radial direction of the nano-homogenizer.

[0021] It should be noted that the homogenizing head is the core component of the high-pressure homogenizer, which is responsible for breaking the material into small and uniform particles through mechanical action. The homogenizing head is used to generate high-intensity shear force, cavitation effect and turbulence to achieve the ideal homogenization effect of the material.

[0022] Optionally, in some embodiments, in the process of obtaining the eddy current pressure values ​​of the homogenizer head in each radial direction, the pressure values ​​of the homogenizer head in each direction are collected in real time by an annular array pressure sensor as the eddy current pressure values ​​in each radial direction. In specific implementation, the pressure value unit of the collection device can be set to MPa, and the sampling frequency can be as low as 1kHz, so as to avoid distortion of the eddy current pressure value data. The number of radial units can be set to 4 or 8 directions of the homogenizer head in the annular direction, and this application does not limit this.

[0023] In step S102, an eddy current pressure characteristic vector is constructed from the eddy current pressure values ​​in various directions, and the material eddy current offset direction and the material eddy current offset length are determined by the eddy current pressure characteristic vector.

[0024] It should be noted that the material vortex offset direction and the material vortex offset length described in this application are state parameters for quantifying the fluid dynamics in the homogenizing head, and are used to judge the uniformity of the shear force distribution of the material particles in the vortex in this application. The material vortex offset direction refers to the deviation angle of the center of gravity of the high-speed rotating material vortex in the homogenizing head relative to the geometric center. The opposite direction of the offset direction points to the area with lower pressure, indicating that the shear force on this side is insufficient, which may easily lead to insufficient crushing of large material particles. The material vortex offset length is used to quantitatively characterize the distance that the rotation center of the material vortex deviates from the geometric center. The larger the material vortex offset length, the greater the degree of deviation of the rotation center of the material vortex from the homogenizing head.

[0025] Optionally, in some embodiments, constructing an eddy pressure characteristic vector from eddy pressure values ​​in various directions, and determining the material eddy deviation direction and material eddy deviation length by using the eddy pressure characteristic vector specifically includes: Obtaining eddy current pressure values ​​in all directions to perform pressure dispersion detection, obtaining eddy current pressure dispersion corresponding to the eddy current pressure values, and normalizing the eddy current pressure values ​​in all directions according to the maximum eddy current pressure value; According to the normalized eddy pressure values ​​in each direction, eddy pressure characteristic vectors are constructed respectively, and the eddy pressure characteristic vectors corresponding to each direction are obtained; The eddy pressure characteristic vectors corresponding to each direction are vector-fused to obtain the material eddy current offset vector. The corresponding material eddy current offset direction and material eddy current offset length are determined according to the eddy current pressure dispersion corresponding to the eddy current pressure value and the material eddy current offset vector.

[0026] It should be noted that the eddy pressure dispersion described in the present application is used to measure the unevenness of pressure distribution and adjust the material eddy offset length based on the unevenness of pressure distribution. In specific implementation, the standard deviation of the eddy pressure values ​​in each direction can be used as the eddy pressure dispersion; optionally, in some embodiments, eddy pressure characteristic vectors are constructed respectively according to the normalized eddy pressure values ​​in each direction, and the eddy pressure characteristic vectors corresponding to each direction are obtained, which specifically includes: constructing a radial two-dimensional plane corresponding to the annular detection plane of the annular array pressure sensor, taking the direction corresponding to the eddy pressure value in the radial two-dimensional plane as the vector direction of its corresponding eddy pressure characteristic vector, and taking the normalized numerical value of the eddy pressure value as the vector length of its corresponding eddy pressure characteristic vector, and then after obtaining the eddy pressure characteristic vectors corresponding to each direction, the eddy pressure characteristic vectors corresponding to each direction are vector fused to obtain the material eddy offset vector, and the vector length of the material eddy offset vector is linearly adjusted according to the eddy pressure dispersion.

[0027] Optionally, in some embodiments, the ratio between the eddy pressure dispersion and the preset standard eddy pressure dispersion is used as an adjustment coefficient to linearly adjust the vector length of the material eddy offset vector, thereby increasing the opening of the servo controller when the pressure distribution is relatively uneven, thereby achieving more precise servo control.

[0028] In step S103, control parameters of a servo controller are determined according to the material vortex deviation direction and the material vortex deviation length, and the servo controller is used to perform a servo control on the feed gravity center of the homogenizing head.

[0029] It should be noted that the servo controller described in this application is a control device for dynamically adjusting the fluid pressure distribution inside the homogenizing head, thereby forming a stable vortex when the material passes through the homogenizing gap. The servo controller is used to compensate in real time for the uneven pressure problem caused by mechanical wear or installation deviation. In specific implementation, the servo controller is respectively connected to the feed valves in each radial direction, and the feed pressure in each radial area is adjusted by the servo controller, thereby eliminating the vortex asymmetry caused by the eccentricity of the homogenizing rod / seat.

[0030] Optionally, in some embodiments, the control parameters of the servo controller are determined according to the material eddy current offset direction and the material eddy current offset length, and the process of using the servo controller to perform a servo control on the feed gravity center of the homogenizing head specifically includes: Determining a target compensation angle range of the servo controller according to the material eddy current deviation direction; For all feed valves within the target compensation angle range, a compensation weight is determined based on the offset angle between the corresponding direction of each feed valve and the material vortex offset direction, and a control compensation amount corresponding to each feed valve connected to the servo controller is determined based on the material vortex offset length and the compensation weight; According to the control compensation amount and compensation weight corresponding to each feed valve, the opening of each feed valve is servo-controlled by the servo controller, thereby realizing a servo control of the feed center of gravity of the homogenizing head.

[0031] In specific implementation, the angle range of ±90° with respect to the material vortex deviation direction is used as the target compensation angle range. For each feed valve within the target compensation angle range, a linear compensation weight is allocated according to the angle between the feed angle of the feed valve relative to the homogenizing head and the material vortex deviation direction, thereby obtaining the product between the compensation weight corresponding to each feed valve within the target compensation angle range and the control compensation amount, and performing compensation mapping according to a preset compensation amount mapping table to obtain the target opening when the opening of the feed valve is controlled. That is, the larger the compensation weight and the control compensation amount, the larger the target opening corresponding to the feed valve. In some embodiments, multiple PID controllers corresponding to the feed valves can be used together as servo controllers to control the opening of the feed valve, thereby balancing the unevenness of the vortex pressure in the homogenizing head. The proportional adjustment coefficient, integral adjustment coefficient and differential adjustment coefficient of the PID controller are calibrated to 1, 0.1 and 0.01 based on experience.

[0032] In step S104, the delayed particle size characteristics of the material are obtained, and servo control detection is performed based on the delayed particle size characteristics of the material and the eddy current offset length of the material to obtain the eddy current control adjustment factor of the homogenizing head.

[0033] It should be noted that the material detection equipment has a time delay in detecting the output material particle size, and it is difficult to control the feed center of gravity by detecting the output material particle size in a timely manner. Therefore, this application does not directly use the material particle size as the feedback parameter of the servo controller, but adjusts the response speed of the servo controller based on the change law between the material delayed particle size characteristics and the material eddy current offset length, thereby improving the servo controller's control accuracy over the feed center of gravity. Optionally, in some embodiments, the material particle size output by the homogenizing head is detected at equal intervals by a particle size detection device to obtain the material delayed particle size characteristics, and the material delayed particle size The characteristics include multiple material detection particle sizes and their corresponding detection times, among which a non-invasive dynamic light scattering or laser diffractometer can be used as the particle size detection equipment. In specific implementation, the detection and installation position of the particle size detection equipment can be five times the pipe diameter downstream of the homogenizer head outlet wall, and the sampling frequency is linearly adjusted in the range of 100-500ms / time according to the material flow rate. In some other embodiments of the present application, other equipment can also be used as particle size detection equipment, or other devices or equipment capable of material particle size detection can be used to collect or obtain the delayed particle size characteristics of the material. This application does not elaborate on this.

[0034] It should be noted that the eddy current control adjustment factor is an array containing static particle size control characteristics and dynamic particle size control characteristics as control parameters. The eddy current control adjustment factor is determined according to the change trend of the material detection particle size after a servo control, reflecting the control sensitivity of the material detection particle size when it is subject to a single servo control. The servo controller is subjected to secondary servo control based on the eddy current control adjustment factor, which can achieve precise control of the shearing process of the material eddy current and improve the working accuracy of the homogenizer. Preferably, in some embodiments, the servo control detection is performed based on the material delayed particle size characteristics and the material eddy current offset length, and the eddy current control adjustment factor of the homogenizing head is obtained, which specifically includes: Obtaining each material detection particle size and its corresponding detection time in the material delayed particle size feature, performing particle size control trend extraction based on each material detection particle size and its corresponding detection time, obtaining a particle size control trend corresponding to the material detection particle size, and extracting a particle size static control feature based on the particle size control trend; Obtaining the eddy current offset length of each material and the time tag corresponding to each eddy current offset length of each material, performing time series fitting on the eddy current offset length of each material based on the time tag to obtain a material eddy current length model; Based on the material eddy length model, the particle size control trend is subjected to correlation feature learning to determine the particle size dynamic control feature, and the eddy control adjustment factor is composed of the particle size static control feature and the particle size dynamic control feature.

[0035] Optionally, in some embodiments, extracting the particle size control trend based on the detected particle sizes of the materials and their corresponding detection times, and obtaining the particle size control trend corresponding to the detected particle sizes of the materials specifically includes: Obtaining a preset target material particle size, and performing time series prediction on the detection particle sizes of various materials and their corresponding detection times based on the target material particle size to obtain a material detection particle size prediction sequence; The material detection particle size prediction sequence is sequence-decomposed to obtain multiple intrinsic mode functions of the material detection particle sizes, and the mean of the intrinsic mode functions of the respective material detection particle sizes is used as the particle size control trend corresponding to the material detection particle size.

[0036] Optionally, in some embodiments, based on the target material particle size, each material detection particle size and its corresponding detection time are predicted in a time series manner. In the process of obtaining the material detection particle size prediction sequence, a moving average autoregressive model corresponding to the material detection particle size can be constructed according to each material detection particle size and its corresponding detection time, and the prediction sequence from the moving average autoregressive model of the material detection particle size to the target material particle size is intercepted as the material detection particle size prediction sequence. The following is a specific embodiment of determining the material detection particle size prediction sequence provided by the present application: the preset modeling cycle is 10 feeding cycles. At this time, the material detection particle size values ​​of the production line in the past 120s can be recorded separately to obtain a historical particle size detection sequence. In other embodiments, the modeling cycle can also be preset to other time lengths; and then a time series graph of the particle size detection sequence can be drawn, the horizontal axis of the time series graph corresponds to different detection moments, and the vertical axis corresponds to the particle size detection value. Then, the time series graph of the particle size detection sequence can be logarithmically transformed to eliminate the influence of dimensional differences in the time series graph.

[0037] Next, based on the time series graph of the particle size detection sequence, an autocorrelation coefficient graph of the particle size detection values ​​is plotted, where the horizontal axis of the autocorrelation coefficient graph represents the number of lag periods (in detection intervals) and the vertical axis represents the autocorrelation coefficient value. A partial autocorrelation coefficient graph of the particle size detection values ​​is also plotted, where the horizontal axis represents the number of lag periods and the vertical axis represents the partial autocorrelation coefficient value.

[0038] According to the characteristics of the autocorrelation coefficient graph and the partial autocorrelation coefficient graph, the order of the model and the range of coefficient values ​​can be preliminarily determined. For example, the autocorrelation coefficient graph can be drawn to observe whether the autocorrelation coefficient shows a tailing feature after a certain order. If the autocorrelation coefficient slowly decays after a certain order and remains within the confidence interval, the order of the moving average model can be preliminarily determined; the partial autocorrelation coefficient graph can be drawn to observe whether the partial autocorrelation coefficient shows a truncation feature after a certain order. If the partial autocorrelation coefficient drops sharply after a certain order and remains near 0, the order of the autoregressive model can be preliminarily determined.

[0039] In specific implementation, we can first find the last significant partial autocorrelation coefficient according to the partial autocorrelation coefficient graph, which is the order of the autoregressive model. For example, if the last significant partial autocorrelation coefficient in the partial autocorrelation coefficient graph is at the 2nd order, the order of the autoregressive model is 2; then, according to the autocorrelation coefficient graph, we can find the last significant autocorrelation coefficient, which is the order of the moving average model. For example, if the last significant autocorrelation coefficient in the autocorrelation coefficient graph is at the 1st order, the order of the moving average model is 1; finally, according to the autocorrelation coefficient graph and the partial autocorrelation coefficient graph, we can determine the order (p,q) of the autoregressive moving average model. For example, if the partial autocorrelation coefficient graph is truncated after the 2nd order and the autocorrelation coefficient graph is tailed after the 1st order, the order of the autoregressive moving average model is (2,1).

[0040] Then, according to the order of the autoregressive moving average model, appropriate parameters are selected to establish an autoregressive moving average model of the particle size detection sequence. The particle size detection sequence is brought into the autoregressive moving average model, and subsequent particle size detection values ​​can be predicted, wherein the particle size prediction value at the end of the next production batch is used as the particle size control reference value.

[0041] In specific implementation, for example, the maximum likelihood estimation method can be used to perform parameter estimation and significance test on the model autoregressive and moving average processes. In some embodiments, the test level of the significance test is 0.01. Finally, the most suitable autoregressive moving average model parameters are selected according to the AIC information criterion to determine the final autoregressive moving average model of the particle size detection value.

[0042] Optionally, in some embodiments, in the process of performing sequence decomposition on the material detection particle size prediction sequence to obtain multiple intrinsic mode functions of the material detection particle size, the material detection particle size prediction sequence is first normalized and then fitted, and the fitting function is subjected to empirical mode decomposition to obtain corresponding multiple intrinsic mode functions; then, the mean of the intrinsic mode function of each material detection particle size is used as the particle size control trend corresponding to the material detection particle size. In specific implementation, the average change rate of the particle size control trend corresponding to the material detection particle size is used as the particle size static control feature.

[0043] Optionally, in some embodiments, the particle size control trend is subjected to correlation feature learning based on the material vortex length model, and in the process of determining the vortex control adjustment factor, the Pearson correlation coefficient between the material vortex length model and the particle size control trend is used as the particle size dynamic control feature.

[0044] In step S105 , the control parameters of the servo controller are corrected based on the eddy current control adjustment factor of the homogenizing head, and the servo controller is used to perform secondary servo control on the feed gravity center of the homogenizing head.

[0045] It should be noted that the present application uses the delayed particle size characteristics of the material and the eddy current offset length of the material for servo control detection, and corrects the control parameters of the servo controller through the change trend between the delayed particle size characteristics of the material and the eddy current offset length of the material over a period of time. The servo control parameters can be controlled in real time according to the material particle size results, thereby improving the response speed of the servo control device.

[0046] Optionally, in some embodiments, correcting the control parameters of the servo controller based on the eddy current control adjustment factor of the homogenizing head specifically includes: Obtaining the particle size static control feature and the material eddy current dynamic feature in the eddy current control adjustment factor of the homogenizing head, and weightedly fusing the particle size static control feature and the material eddy current dynamic feature based on preset static weight coefficients and dynamic weight coefficients to obtain a servo correction coefficient; The integral adjustment coefficient of the servo controller is corrected according to the servo correction coefficient.

[0047] In specific implementation, the servo correction coefficient = α·static control characteristic of particle size + β·static control characteristic of particle size, wherein α and β are the static weight coefficient and the dynamic weight coefficient respectively. The integral adjustment coefficient of the servo controller after correction = the servo correction coefficient × the integral adjustment coefficient of the servo controller before correction. The present application adopts multiple PID controllers corresponding to the feed valves as servo controllers to control the opening of the feed valves, thereby balancing the unevenness of the eddy pressure in the homogenizing head. The process of correcting the control parameters of the servo controller is the process of jointly correcting the control parameters of the multiple PID controllers corresponding to the feed valves.

[0048] In addition, in another aspect of the present application, in some embodiments, the present application provides an intelligent servo drive control system for a nano homogenizer, the device including a servo control unit, Figure 2 , which is a schematic diagram of exemplary hardware and / or software of a servo control unit according to some embodiments of the present application. The servo control unit 200 includes: an eddy current pressure acquisition module 201, an eddy current offset detection module 202, a first servo control module 203, and a second servo control module 204, which are described as follows: The eddy current pressure acquisition module 201 is used to start the nano homogenizer control and obtain the eddy current pressure value of the homogenizing head in each radial direction of the nano homogenizer; The eddy current offset detection module 202 constructs an eddy current pressure characteristic vector from the eddy current pressure values ​​in each direction, and determines the material eddy current offset direction and material eddy current offset length through the eddy current pressure characteristic vector; The first servo control module 203 is used to determine the control parameters of the servo controller according to the material eddy current offset direction and the material eddy current offset length, and use the servo controller to perform a servo control on the feed center of gravity of the homogenizing head; The second servo control module 204 is used to obtain the delayed particle size characteristics of the material, perform servo control detection based on the delayed particle size characteristics of the material and the eddy current offset length of the material, and obtain the eddy current control adjustment factor of the homogenizing head; The second servo control module 204 is further configured to calibrate the control parameters of the servo controller based on the eddy current control adjustment factor of the homogenizing head, and perform secondary servo control on the feed gravity center of the homogenizing head using the servo controller.

[0049] The above describes in detail an example of an intelligent servo drive control method and system for a nano-homogenizer provided in an embodiment of the present application. It can be understood that in order to achieve the above functions, the corresponding device includes a hardware structure and / or software module corresponding to each function.

[0050] Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function in the application is executed in hardware or in a computer software-driven hardware manner depends on the specific application and design constraints of the technical solution. Therefore, professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0051] In addition, the present application also provides a computer terminal device, which includes a memory and a processor, the memory stores a code, and the processor is configured to obtain the code and execute the above-mentioned intelligent servo drive control method for a nano homogenizer.

[0052] In some embodiments, reference Figure 3 , which is a schematic diagram of the structure of a computer terminal device that applies an intelligent servo drive control method for a nano homogenizer according to some embodiments of the present application. The intelligent servo drive control method for a nano homogenizer in the above embodiment can be used by Figure 3 The computer terminal device 300 shown in FIG. 1 is implemented as shown in FIG. 1 , and the computer terminal device 300 includes at least one communication bus 301 , a communication interface 302 , a processor 303 and a memory 304 .

[0053] The processor 303 can be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more processors for controlling the execution of an intelligent servo drive control method for a nano-homogenizer in the present application.

[0054] The communication bus 301 may include a path for transmitting information between the aforementioned components.

[0055] Memory 304 may be, but is not limited to, a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, a random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, an optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer. Memory 304 may be independent and connected to processor 303 via communication bus 301. Memory 304 may also be integrated with processor 303.

[0056] Memory 304 is used to store program code for executing the solution of the present application, and is controlled by processor 303 for execution. Processor 303 is used to execute the program code stored in memory 304. The program code may include one or more software modules. In the above embodiment, the determination of the material eddy current offset length can be implemented by processor 303 and one or more software modules in the program code in memory 304.

[0057] The communication interface 302 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.

[0058] Optionally, the computer terminal device 300 may further include a power supply 305 for providing power to various devices or circuits in the real-time computer terminal device.

[0059] In a specific implementation, as an example, a computer terminal device may include multiple processors, each of which may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0060] The aforementioned computer terminal device can be a general-purpose computer terminal device or a dedicated computer terminal device. In a specific implementation, the computer terminal device can be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of this application do not limit the type of computer terminal device.

[0061] In addition, in other aspects of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores at least one computer program, and the computer program is loaded and executed by a processor to implement the operations performed by the above-mentioned intelligent servo drive control method for a nano homogenizer.

[0062] In summary, in an embodiment of the present application, an intelligent servo drive control method and system for a nano homogenizer is disclosed. First, the eddy current pressure value of the homogenizer head in each radial direction in the nano homogenizer is obtained by starting the nano homogenizer control; the eddy current pressure characteristic vector is constructed from the eddy current pressure values ​​in each direction, and the material eddy current offset direction and the material eddy current offset length are determined by the eddy current pressure characteristic vector; the control parameters of the servo controller are determined according to the material eddy current offset direction and the material eddy current offset length, and the servo controller is used to perform a servo control on the feeding center of gravity of the homogenizer head; the material delayed particle size characteristics are obtained, and servo control detection is performed based on the material delayed particle size characteristics and the material eddy current offset length to obtain the eddy current control adjustment factor of the homogenizer head; the control parameters of the servo controller are corrected based on the eddy current control adjustment factor of the homogenizer head, and the servo controller is used to perform a secondary servo control on the feeding center of gravity of the homogenizer head, which can perform servo control on the feeding center of gravity of the homogenizer head according to the material eddy current offset situation, so that the nano homogenizer does not need to be frequently stopped for inspection, thereby improving the working efficiency of the nano homogenizer.

[0063] The above description is merely an embodiment of the present application. Common knowledge such as the specific technical solutions or features of the solutions is not described in detail herein. It should be noted that those skilled in the art may make various modifications and improvements without departing from the technical solution of the present application, and these modifications and improvements should also be considered within the scope of protection of the present application. These modifications and improvements will not affect the effectiveness of the implementation of the present application or the practical application of the patent.

[0064] The scope of protection claimed by this application shall be determined by the content of the claims. The specific embodiments and other descriptions in the specification may be used to interpret the content of the claims. Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of the invention. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application is intended to include such modifications and variations.

Claims

1. An intelligent servo drive control method for a nano homogenizer, characterized in that: include: Starting the nano homogenizer control to obtain the eddy current pressure value of the homogenizing head in each radial direction of the nano homogenizer; The eddy current pressure characteristic vector is constructed from the eddy current pressure values ​​in each direction, and the eddy current offset direction and the eddy current offset length of the material are determined by the eddy current pressure characteristic vector; Determining control parameters of a servo controller according to the material eddy current offset direction and the material eddy current offset length, and using the servo controller to perform a servo control on the feed center of gravity of the homogenizing head; Obtaining the delayed particle size characteristics of the material, performing servo control detection based on the delayed particle size characteristics of the material and the eddy current offset length of the material, and obtaining the eddy current control adjustment factor of the homogenizing head; The control parameters of the servo controller are corrected based on the eddy current control adjustment factor of the homogenizing head, and the servo controller is used to perform secondary servo control on the feeding center of gravity of the homogenizing head.

2. The method according to claim 1, wherein Determining control parameters of a servo controller according to the material eddy current offset direction and the material eddy current offset length, and using the servo controller to perform a servo control on the feed center of gravity of the homogenizing head specifically includes: Determining a target compensation angle range of the servo controller according to the material eddy current deviation direction; For all feed valves within the target compensation angle range, a compensation weight is determined based on the offset angle between the corresponding direction of each feed valve and the material vortex offset direction, and a control compensation amount corresponding to each feed valve connected to the servo controller is determined based on the material vortex offset length and the compensation weight; According to the control compensation amount and compensation weight corresponding to each feed valve, the opening of each feed valve is servo-controlled by the servo controller.

3. The method according to claim 1, wherein Correcting the control parameters of the servo controller based on the eddy current control adjustment factor of the homogenizing head specifically includes: Obtaining the particle size static control feature and the material eddy current dynamic feature in the eddy current control adjustment factor of the homogenizing head, and weightedly fusing the particle size static control feature and the material eddy current dynamic feature based on preset static weight coefficients and dynamic weight coefficients to obtain a servo correction coefficient; The integral adjustment coefficient of the servo controller is corrected according to the servo correction coefficient.

4. The method according to claim 1, wherein In the process of obtaining the delayed particle size characteristics of the material, the particle size output by the homogenizing head is detected at equal intervals by a particle size detection device to obtain the delayed particle size characteristics of the material. The delayed particle size characteristics of the material include multiple material detection particle sizes and their corresponding detection times.

5. The method according to claim 1, wherein The eddy current pressure characteristic vector is constructed from the eddy current pressure values ​​in each direction. The eddy current pressure characteristic vector is used to determine the material eddy current deviation direction and the material eddy current deviation length. Specifically, the following steps are performed: Obtaining eddy current pressure values ​​in all directions to perform pressure dispersion detection, obtaining eddy current pressure dispersion corresponding to the eddy current pressure values, and normalizing the eddy current pressure values ​​in all directions according to the maximum eddy current pressure value; According to the normalized eddy pressure values ​​in each direction, eddy pressure characteristic vectors are constructed respectively, and the eddy pressure characteristic vectors corresponding to each direction are obtained; The eddy pressure characteristic vectors corresponding to each direction are vector-fused to obtain the material eddy current offset vector. The corresponding material eddy current offset direction and material eddy current offset length are determined according to the eddy current pressure dispersion corresponding to the eddy current pressure value and the material eddy current offset vector.

6. The method according to claim 1, wherein In the process of obtaining the eddy current pressure values ​​of the homogenizing head in each radial direction in the nano homogenizer, the pressure values ​​of each direction of the homogenizing head are collected in real time by the annular array pressure sensor as the eddy current pressure values ​​in each radial direction.

7. The method according to claim 1, wherein Servo control detection is performed based on the delayed particle size characteristics of the material and the eddy current offset length of the material to obtain the eddy current control adjustment factor of the homogenizing head, which specifically includes: Obtaining each material detection particle size and its corresponding detection time in the material delayed particle size feature, performing particle size control trend extraction based on each material detection particle size and its corresponding detection time, obtaining a particle size control trend corresponding to the material detection particle size, and extracting a particle size static control feature based on the particle size control trend; Obtaining the eddy current offset length of each material and the time tag corresponding to each eddy current offset length of each material, performing time series fitting on the eddy current offset length of each material based on the time tag to obtain a material eddy current length model; Based on the material eddy length model, the particle size control trend is subjected to correlation feature learning to determine the particle size dynamic control feature, and the eddy control adjustment factor is composed of the particle size static control feature and the particle size dynamic control feature.

8. An intelligent servo drive control system for a nano homogenizer, comprising a servo control unit, characterized in that: The servo control unit comprises: The eddy current pressure acquisition module is used to start the nano homogenizer control and obtain the eddy current pressure value of the homogenizing head in each radial direction of the nano homogenizer; The eddy current offset detection module constructs an eddy current pressure characteristic vector from the eddy current pressure values ​​in each direction, and determines the material eddy current offset direction and material eddy current offset length through the eddy current pressure characteristic vector; a first servo control module, configured to determine control parameters of a servo controller according to the material eddy current offset direction and the material eddy current offset length, and perform a servo control on the feed center of gravity of the homogenizing head using the servo controller; A second servo control module is used to obtain the delayed particle size characteristics of the material, perform servo control detection based on the delayed particle size characteristics of the material and the eddy current offset length of the material, and obtain the eddy current control adjustment factor of the homogenizing head; The second servo control module is further configured to calibrate the control parameters of the servo controller based on the eddy current control adjustment factor of the homogenizing head, and perform secondary servo control on the feed gravity center of the homogenizing head using the servo controller.

9. A computer terminal device, characterized in that: The computer terminal device includes a memory and a processor, the memory stores a code, and the processor is configured to obtain the code and execute the intelligent servo drive control method for a nano homogenizer according to any one of claims 1 to 7.

10. A computer-readable storage medium storing at least one computer program, characterized in that: The computer program is loaded and executed by a processor to implement the operations performed by the intelligent servo drive control method for a nano-homogenizer according to any one of claims 1 to 7.

Images