Intelligent control system and method for rotating speed of centrifugal machine

Abstract

The invention discloses an intelligent control system and method for the rotating speed of a centrifugal machine, relates to the technical field of centrifugal machine control, and solves the technical problem that in the prior art, when the rotating speed of the centrifugal machine is adjusted, the influence of equipment abrasion on the centrifugal machine is neglected, so that the adjusting speed cannot meet the requirement, and the rotating speed control efficiency of the centrifugal machine is low. Inputting the detection image into a material category identification model to obtain a category label; searching an initial rotating speed according to the category label and the material weight; calculating an equipment wear coefficient according to historical equipment data, calculating an equipment adjustment rotating speed according to the equipment wear coefficient, and assigning the equipment adjustment rotating speed to the equipment rotating speed; calculating a centrifugal machine abnormal coefficient after calculating a vibration abnormal coefficient according to the equipment data; the alarm signal is generated according to the abnormal coefficient of the centrifugal machine, equipment parameters of the centrifugal machine are accurately obtained through multivariate data, the rotating speed difference caused by equipment abrasion is considered, the rotating speed of the centrifugal machine is dynamically adjusted, the state of the centrifugal machine is monitored in real time, and the rotating speed control efficiency of the centrifugal machine is improved.

Description

Technical Field

[0001] The present application belongs to the field of centrifuge control technology, and specifically is an intelligent control system and method for centrifuge speed. Background Art

[0002] A centrifuge is a machine that uses centrifugal force to separate different substances. It is widely used in chemical, petroleum, food, pharmaceutical and water treatment sectors. It mainly uses an electric motor to drive the rotor to rotate at high speed. The centrifugal force generated separates substances of different densities and particle sizes in suspensions or emulsions. Centrifuges are mainly classified based on structure, separation method and speed. They can be divided into desktop centrifuges, vertical centrifuges and filter centrifuges. The speed control of the centrifuge is the key to ensure its normal operation and efficient separation. The use of appropriate speed control methods and flexible adjustment according to specific application scenarios and material characteristics can give full play to the performance advantages of the centrifuge.

[0003] The prior art (invention patent application with publication number CN113909006A) discloses a method for temperature control of a centrifuge, wherein the centrifuge includes a refrigeration system consisting of a compressor, an evaporator, a condenser and a thermal expansion valve; the method includes: determining a reference temperature t; detecting the temperature in the centrifuge cavity to obtain a temperature detection value t; calculating a difference Δt between the temperature detection value t and the reference temperature t; and when the absolute value of the difference Δt is greater than or equal to a preset threshold, adjusting the rotation speed of the variable frequency compressor to make the temperature in the centrifuge cavity close to the target temperature.

[0004] In the above case, the speed of the centrifuge is adjusted by detecting the difference between the temperature in the centrifuge chamber and the reference temperature and comparing it with the preset threshold. Since the theoretical speed and the set speed of the centrifuge may be affected by equipment wear, the actual speed after the set speed cannot reach the theoretical speed, so that the actual speed of the centrifuge does not meet the requirements, resulting in low speed control efficiency of the centrifuge. Therefore, the control method of the centrifuge speed still needs to be further improved. Summary of the invention

[0005] The present application aims to solve at least one of the technical problems existing in the prior art; to this end, the present application proposes an intelligent control system and method for the speed of a centrifuge, which is used to solve the technical problem that the prior art ignores the influence of equipment wear on the centrifuge when adjusting the speed of the centrifuge, so that the adjustment speed fails to meet the requirements, resulting in low speed control efficiency of the centrifuge.

[0006] To achieve the above-mentioned purpose, the first aspect of the present application provides an intelligent control system for centrifuge speed, comprising: a data acquisition module, a data analysis module, a control module, an early warning module and a database;

[0007] The data acquisition module is used to acquire equipment data and material data through data acquisition equipment;

[0008] The data analysis module: inputs the detection image in the material data into the material category recognition model to obtain the category label; searches for the initial rotation speed according to the category label and the material weight; calculates the equipment wear coefficient according to the historical equipment data; calculates the equipment adjustment speed according to the equipment wear coefficient and the initial rotation speed; calculates the centrifuge abnormality coefficient after calculating the vibration abnormality coefficient according to the equipment data; generates an alarm signal according to the centrifuge abnormality coefficient;

[0009] The control module: assigns the device adjustment speed to the device speed;

[0010] The early warning module: makes prompts according to the alarm signal and contacts the management personnel.

[0011] The present application obtains a category label by inputting a detection image in material data into a material category recognition model; searches for an initial rotation speed according to the category label and material weight; calculates an equipment wear coefficient according to historical equipment data; calculates an equipment adjustment rotation speed according to the equipment wear coefficient and the initial rotation speed, and assigns the equipment adjustment rotation speed to the equipment rotation speed; calculates a centrifuge abnormality coefficient after calculating an abnormal vibration coefficient according to equipment data; generates an alarm signal according to the abnormal centrifuge coefficient, accurately obtains equipment parameters of the centrifuge through multivariate data, takes into account the difference in rotation speed caused by equipment wear, dynamically adjusts the centrifuge rotation speed, monitors the status of the centrifuge in real time, and improves the speed control efficiency of the centrifuge.

[0012] Furthermore, the material category recognition model is constructed through an artificial intelligence model, including:

[0013] Obtain several historical detection images and their corresponding category labels;

[0014] Divide the historical detection images into training data, verification data and test data according to category labels; perform data preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set;

[0015] Select an AI model as the base model;

[0016] Train the basic model with the training set, and adjust the learning rate on the validation set to obtain the pre-trained model;

[0017] By verifying the pre-trained model on the test set, we finally get a material category recognition model that inputs a detection image and outputs a category label.

[0018] Further, searching for the initial rotation speed according to the category label and the material weight includes:

[0019] Get the category label and its corresponding material concentration and material weight;

[0020] Integrate category labels and their corresponding material concentrations and material weights into comprehensive data;

[0021] The comprehensive data were input into the speed-time prediction model to obtain the initial rotation speed and centrifugation time.

[0022] Furthermore, the speed time prediction model is constructed by a neural network model, including:

[0023] Obtain several historical category labels, material concentrations and material weights and their corresponding equipment speeds and centrifugation times; integrate the historical category labels, material concentrations and material weights into historical comprehensive data;

[0024] And divide it into training data, verification data and test data according to the equipment rotation speed and centrifugation time; perform data preprocessing on the training data, verification data and test data to obtain the training set, verification set and test set;

[0025] Select the neural network model as the base model;

[0026] Train the basic model with the training set, and adjust the learning rate or other hyperparameters on the validation set to obtain the pre-trained model;

[0027] By verifying the pre-trained model on the test set, we finally get the input comprehensive data, and the output is the speed-time prediction model of the equipment speed and centrifugal time.

[0028] The present application obtains the initial speed and centrifugation time by inputting the factors affecting the centrifuge speed and centrifugation time into the pre-trained speed-time prediction model. The prediction results obtained by the network model are more accurate, providing an accurate basis for speed adjustment and improving the adjustment speed of equipment parameters.

[0029] Furthermore, the calculation of the equipment wear coefficient according to the historical equipment data includes:

[0030] Obtain historical equipment working data and historical equipment environment data in the historical equipment data; the historical equipment working data includes low-load working time DFZi and high-load working time GFZj; the historical equipment environment data includes temperature and humidity under several different load data of the centrifuge equipment; the high-load working time refers to the working time of the centrifuge exceeding the normal working load upper limit by n%; the low-load working time refers to the working time of the centrifuge below the normal working load upper limit by (100-n)%, wherein 0 <n<100;

[0031] Generate corresponding environmental impact coefficients DHYXi and GHYXj according to the temperature and humidity under several different load data of the centrifuge equipment;

[0032] The equipment wear coefficient SMX of the centrifuge equipment is calculated by the formula SMX=1-exp(-(α1×∑(DFZi / DT×(1+DHYXi))+α2×∑(GFZj / DT×(1+GHYXj)))); wherein α1 and α2 are weight coefficients, α1 and α2∈(0,1), and α1<α2; DT is the unit time; i represents the number of the low-load working time of the centrifuge equipment, i=1, 2,…, M, and M is the total number of low-load working times; j represents the number of the high-load working time of the centrifuge equipment, j=1, 2,…, N, and N is the total number of high-load working times.

[0033] Furthermore, the generation of corresponding environmental impact coefficients DHYXi and GHYXj according to the temperature and humidity under several different load data of the centrifuge equipment includes:

[0034] Obtain the working temperatures DWi and DSi corresponding to the low-load working time, the working temperature GWj and working humidity GSj corresponding to the high-load working time, and the optimum working temperature W and the optimum working humidity S;

[0035] Calculate the temperature influence coefficients DWYXi and GWYXj by the formula;

[0036] DWYXi=1-exp(-(|DWi-W| / DW)^βw);

[0037] GWYXj=1-exp(-(|GWj-W| / DW)^βw);

[0038] Calculate humidity influence coefficients DSYXi and GSYXj by formula;

[0039] DSYXi=1-exp(-(|DSi-S| / DS)^βs);

[0040] GSYXj=1-exp(-(|GSj-S| / DS)^βs);

[0041] Calculate the environmental impact coefficients DHYXi and GHYXj through the formula;

[0042] DHYXi=α3×DWYXi+α4×DSYXi;

[0043] GHYXj=α3×GWYXj+α4×GSYXj; wherein α3 and α4 are weight coefficients, α3 and α4∈(0,1); DW is unit temperature, DS is unit humidity, βs and βw are exponential coefficients, βs and βw∈(0,1).

[0044] Further, the step of calculating the device adjustment speed according to the device wear coefficient and the initial speed includes:

[0045] Obtain equipment wear coefficient SMX and initial speed CV;

[0046] The equipment adjustment speed STV is calculated by the formula STV=CV / (h×(1-SMX^(1+β1)); wherein h is the proportional coefficient, h∈(0,1); and β1 is the exponential coefficient, β1∈(0,1).

[0047] The present application calculates the wear coefficient of the centrifuge equipment. Before starting the centrifuge, the initial speed is updated by the equipment wear coefficient to obtain the equipment adjustment speed, and the equipment adjustment speed is assigned to the equipment speed of the centrifuge to eliminate the impact of speed reduction caused by equipment wear, thereby improving the accuracy of centrifuge speed control.

[0048] Further, the calculation of the centrifuge abnormality coefficient after calculating the vibration abnormality coefficient according to the equipment data includes:

[0049] Obtain vibration data and equipment wear coefficient SMX from equipment data;

[0050] Calculate the vibration abnormality coefficient ZYX based on the vibration data;

[0051] The centrifuge abnormality coefficient LYX is calculated by the formula LYX=α5×SMX+α6×ZYX; wherein α5 and α6 are weight coefficients, α5 and α6∈(0,1).

[0052] Further, the calculation of the vibration abnormality coefficient ZYX according to the vibration data includes:

[0053] Obtain the vibration speed ZS and the vibration amplitude ZF in the vibration data as well as the standard vibration speed BZS and the standard vibration amplitude BZF;

[0054] When the vibration speed is less than the standard vibration speed, the vibration speed impact value is set to 0; otherwise, the vibration speed impact value is the absolute value ZSY of the difference between the vibration speed and the standard vibration speed;

[0055] When the vibration amplitude is less than the standard vibration amplitude, the vibration amplitude impact value is set to 0; otherwise, the vibration amplitude impact value is the absolute value ZFY of the difference between the vibration amplitude and the standard vibration amplitude;

[0056] The vibration abnormality coefficient ZYX is calculated by the formula ZYX=1-exp(-(α7×ZSY / DS+α8×ZFY / DF)); wherein α7 and α8 are weight coefficients, α7 and α8∈(0,1).

[0057] The present application obtains the equipment wear coefficient according to the historical equipment data, and can accurately obtain the equipment abnormality that affects the centrifuge speed. At the same time, the vibration abnormality coefficient is calculated through the vibration data of the centrifuge to obtain the vibration abnormality of the centrifuge. The state of the centrifuge is considered from multiple aspects and the centrifuge abnormality coefficient is calculated accordingly, which provides higher detection accuracy and efficiency for the abnormal state detection of the centrifuge.

[0058] Further, the generating of an alarm signal according to the centrifuge abnormality coefficient includes:

[0059] Obtain centrifuge abnormality coefficient, equipment wear coefficient and vibration abnormality coefficient;

[0060] When the centrifuge abnormality coefficient is greater than the equipment abnormality threshold, an equipment failure alarm signal is generated;

[0061] Otherwise, determine whether the equipment wear coefficient is greater than the wear threshold, if yes, generate an equipment wear alarm signal; if no, do nothing;

[0062] Determine whether the vibration abnormality coefficient is greater than the vibration threshold. If yes, generate an equipment vibration abnormality alarm signal; if no, do nothing.

[0063] Another aspect of the present invention provides an intelligent control method for centrifuge speed, comprising:

[0064] S0: Get equipment data and material data;

[0065] S1: Input the detection image in the material data into the material category recognition model to obtain the category label; find the initial speed according to the category label and material weight;

[0066] S2: Calculate the equipment wear coefficient according to historical equipment data; calculate the equipment adjustment speed according to the equipment wear coefficient and the initial speed, and assign the equipment adjustment speed to the equipment speed;

[0067] S3: calculating the centrifuge abnormality coefficient after calculating the vibration abnormality coefficient according to the equipment data; generating an alarm signal according to the centrifuge abnormality coefficient;

[0068] S4: Provide prompts based on alarm signals and contact management.

[0069] Compared with the prior art, the beneficial effects of this application are:

[0070] 1. The present application obtains a category label by inputting a detection image in material data into a material category recognition model; searching for an initial rotation speed according to the category label and material weight; calculating an equipment wear coefficient according to historical equipment data; calculating an equipment adjustment speed according to the equipment wear coefficient and the initial rotation speed, and assigning the equipment adjustment speed to the equipment speed; calculating a centrifuge abnormality coefficient after calculating an abnormal vibration coefficient according to equipment data; generating an alarm signal according to the abnormal centrifuge coefficient, accurately obtaining equipment parameters of the centrifuge through multivariate data, taking into account the difference in rotation speed caused by equipment wear, dynamically adjusting the centrifuge speed, monitoring the status of the centrifuge in real time, and improving the speed control efficiency of the centrifuge.

[0071] 2. This application calculates the wear coefficient of the centrifuge equipment. Before starting the centrifuge, the initial speed is updated by the equipment wear coefficient to obtain the equipment adjustment speed, and the equipment adjustment speed is assigned to the equipment speed of the centrifuge to eliminate the impact of equipment wear on the speed reduction, thereby improving the accuracy of the centrifuge speed control.

[0072] 3. The present application obtains the equipment wear coefficient according to the historical equipment data, and can accurately obtain the equipment abnormality that affects the centrifuge speed. At the same time, the vibration abnormality coefficient is calculated through the vibration data of the centrifuge to obtain the vibration abnormality of the centrifuge. The state of the centrifuge is considered from multiple aspects and the centrifuge abnormality coefficient is calculated accordingly, which provides higher detection accuracy and efficiency for the abnormal state detection of the centrifuge. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0074] Figure 1 This is a schematic diagram of the principle of an intelligent control system for centrifuge speed in the present application;

[0075] Figure 2 A flow chart for generating an alarm signal for the present application;

[0076] Figure 3 This is a flow chart of an intelligent control method for centrifuge speed in the present application. DETAILED DESCRIPTION

[0077] The technical solution of the present application will be described clearly and completely in conjunction with the embodiments below. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0078] See also Figure 1 , the first aspect of the present application provides an intelligent control system for centrifuge speed, including: a data acquisition module, a data analysis module, a control module, an early warning module and a database;

[0079] Data acquisition module: obtain equipment data and material data through data acquisition equipment; equipment data refers to the data of centrifuge equipment, and material data refers to the data of materials that need to be processed by the centrifuge; data acquisition equipment includes high-precision cameras, various sensors, etc.

[0080] Data analysis module: input the detection image in the material data into the material category recognition model to obtain the category label; find the initial speed according to the category label and material weight, which refers to the centrifuge speed that should be reached under the current material state; calculate the equipment wear coefficient according to historical equipment data, which refers to the degree of equipment wear that affects the actual speed of the centrifuge; calculate the equipment adjustment speed according to the equipment wear coefficient and the initial speed, which refers to the equipment speed that needs to be set for the centrifuge to achieve the required speed in consideration of wear; calculate the centrifuge abnormality coefficient after calculating the vibration abnormality coefficient according to the equipment data, which refers to the degree of abnormality of the centrifuge; generate an alarm signal according to the centrifuge abnormality coefficient;

[0081] Control module: assign the device adjustment speed to the device speed;

[0082] Early warning module: Prompts are given based on alarm signals and management personnel are contacted; alarm signals include equipment failure alarm signals, equipment wear alarm signals, and equipment vibration abnormality alarm signals, etc.

[0083] This embodiment obtains a category label by inputting a detection image in the material data into a material category recognition model; searches for an initial rotation speed according to the category label and the material weight; calculates an equipment wear coefficient according to historical equipment data; calculates an equipment adjustment rotation speed according to the equipment wear coefficient and the initial rotation speed, and assigns the equipment adjustment rotation speed to the equipment rotation speed; calculates a centrifuge abnormality coefficient after calculating an abnormal vibration coefficient according to the equipment data; generates an alarm signal according to the abnormal centrifuge coefficient, accurately obtains equipment parameters of the centrifuge through multivariate data, takes into account differences in rotation speed caused by equipment wear, dynamically adjusts the centrifuge rotation speed, monitors the status of the centrifuge in real time, and improves the speed control efficiency of the centrifuge.

[0084] The material category recognition model in this embodiment is constructed by an artificial intelligence model, including:

[0085] Obtain several historical detection images and their corresponding category labels; the category label refers to the type of material that needs to pass through the centrifuge;

[0086] The historical detection images are divided into training data, verification data and test data according to the category labels; the training data, verification data and test data are preprocessed to obtain the training set, verification set and test set; the ratio between the training set, the test set and the verification set is 7:2:1;

[0087] Select an artificial intelligence model as the basic model; the artificial intelligence model includes a BP neural network model and a RBF neural network model;

[0088] Train the basic model with the training set, and adjust the learning rate or other hyperparameters on the validation set to obtain the pre-trained model;

[0089] By verifying the pre-trained model on the test set, we finally get a material category recognition model that inputs a detection image and outputs a category label.

[0090] In this embodiment, searching for the initial rotation speed according to the category label and the material weight includes:

[0091] Get the category label and its corresponding material concentration and material weight;

[0092] Integrate category labels and their corresponding material concentrations and material weights into comprehensive data;

[0093] The comprehensive data were input into the speed-time prediction model to obtain the initial rotation speed and centrifugation time.

[0094] The speed time prediction model in this embodiment is constructed by a neural network model, including:

[0095] Obtain several historical category labels, material concentrations and material weights and their corresponding equipment speeds and centrifugation times; integrate the historical category labels, material concentrations and material weights into historical comprehensive data;

[0096] And divide it into training data, verification data and test data according to the equipment speed and centrifugation time; perform data preprocessing on the training data, verification data and test data to obtain the training set, verification set and test set; the ratio between the training set, test set and verification set is 7:2:1;

[0097] Select the neural network model as the base model;

[0098] Train a basic model with a training set, and adjust the learning rate or other hyperparameters on a validation set to obtain a pre-trained model;

[0099] Verify the pre-trained model on a test set, and finally obtain a speed-time prediction model with the input of comprehensive data and the output of equipment rotation speed and centrifugation time.

[0100] In this embodiment, by inputting the factors affecting the centrifuge rotation speed and centrifugation time into the pre-trained speed-time prediction model to obtain the initial rotation speed and centrifugation time, the result obtained by prediction through the network model is more accurate, providing an accurate basis for speed adjustment and improving the adjustment speed of equipment parameters at the same time.

[0101] Calculating the equipment wear coefficient according to historical equipment data in this embodiment includes:

[0102] Obtain the historical equipment working data and historical equipment environment data in the historical equipment data; the historical equipment working data includes the low-load working duration DFZi and the high-load working duration GFZj; the historical equipment environment data includes the temperature and humidity under several different load data of the centrifuge equipment; the high-load working duration refers to the working duration when the centrifuge exceeds n% of the normal working load upper limit; the low-load working duration refers to the working duration when the centrifuge is lower than (100 - n)% of the normal working load upper limit, where 0 < n < 100; the specific value of n is set according to experience, and n is set to 70 in this embodiment;

[0103] Generate corresponding environmental impact coefficients DHYXi and GHYXj according to the temperature and humidity under several different load data of the centrifuge equipment in this embodiment;

[0104] Calculate the equipment wear coefficient SMX of the centrifuge equipment through the formula SMX = 1 - exp(-(α1×∑(DFZi / DT×(1 + DHYXi)) + α2×∑(GFZj / DT×(1 + GHYXj)))); where α1 and α2 are weight coefficients, α1 and α2 ∈ (0, 1), and α1 < α2, and the specific values are set according to experience; DT is the unit duration, and the specific value is set according to experience, and DT is set to 1 hour in this embodiment; i represents the number of the low-load working duration of the centrifuge equipment, i = 1, 2,..., M, M is the total number of low-load working durations; j represents the number of the high-load working duration of the centrifuge equipment, j = 1, 2,..., N, N is the total number of high-load working durations; the longer the working duration and the greater the environmental impact coefficient, the more serious the equipment wear; therefore, the equipment wear coefficient increases accordingly.

[0105] Generating corresponding environmental impact coefficients DHYXi and GHYXj according to the temperature and humidity under several different load data of the centrifuge equipment in this embodiment includes:

[0106] Obtain the working temperatures DWi and DSi corresponding to the low-load working time, the working temperature GWj and working humidity GSj corresponding to the high-load working time, and the optimum working temperature W and the optimum working humidity S;

[0107] Calculate the temperature influence coefficients DWYXi and GWYXj by the formula;

[0108] DWYXi=1-exp(-(|DWi-W| / DW)^βw);

[0109] GWYXj=1-exp(-(|GWj-W| / DW)^βw); The more the temperature deviates from the optimum working temperature, the more serious the impact of temperature on equipment wear will be, so the temperature anomaly coefficient will increase accordingly;

[0110] Calculate humidity influence coefficients DSYXi and GSYXj by formula;

[0111] DSYXi=1-exp(-(|DSi-S| / DS)^βs);

[0112] GSYXj=1-exp(-(|GSj-S| / DS)^βs); The more the humidity deviates from the optimum working humidity, the more serious the impact of humidity on equipment wear will be, so the humidity anomaly coefficient will increase accordingly;

[0113] Calculate the environmental impact coefficients DHYXi and GHYXj through the formula;

[0114] DHYXi=α3×DWYXi+α4×DSYXi;

[0115] GHYXj=α3×GWYXj+α4×GSYXj; wherein α3 and α4 are weight coefficients, α3 and α4∈(0,1); specific values ​​are set according to experience; DW is unit temperature, DS is unit humidity, specific values ​​are set according to experience, in this embodiment, DW is set to 1°C, DS is set to 1%; βs and βw are exponential coefficients, βs and βw∈(0,1), specific values ​​are set according to experience; with the increase of temperature anomaly coefficient and humidity anomaly coefficient, the environmental anomaly coefficient will also increase accordingly.

[0116] In this embodiment, the device adjustment speed is calculated according to the device wear coefficient and the initial speed, including:

[0117] Obtain equipment wear coefficient SMX and initial speed CV;

[0118] The equipment adjustment speed STV is calculated by the formula STV=CV / (h×(1-SMX^(1+β1)); wherein h is the proportional coefficient, h∈(0,1), and the specific value is set based on experience; β1 is the exponential coefficient, β1∈(0,1), and the specific value is set based on experience; when the initial speed is fixed, as the equipment wear coefficient increases, the greater the degree of equipment wear, in order to achieve the target speed, it is necessary to increase the equipment speed to meet the target speed requirements, so the equipment adjustment speed will also increase accordingly.

[0119] In this embodiment, by calculating the wear coefficient of the centrifuge equipment, before starting the centrifuge, the initial speed is updated by the equipment wear coefficient to obtain the equipment adjustment speed, and the equipment adjustment speed is assigned to the equipment speed of the centrifuge to eliminate the influence of speed reduction caused by equipment wear, thereby improving the accuracy of centrifuge speed control.

[0120] In this embodiment, the calculation of the centrifuge abnormality coefficient after calculating the vibration abnormality coefficient according to the equipment data includes:

[0121] Obtain vibration data and equipment wear coefficient SMX from equipment data; vibration data includes vibration speed and vibration amplitude, etc.;

[0122] Calculate the vibration abnormality coefficient ZYX based on the vibration data;

[0123] The centrifuge abnormality coefficient LYX is calculated by the formula LYX=α5×SMX+α6×ZYX; wherein α5 and α6 are weight coefficients, α5 and α6∈(0,1), and the specific values ​​are set according to experience; the centrifuge abnormality coefficient increases with the increase of the equipment wear coefficient and the vibration abnormality coefficient.

[0124] Calculating the vibration abnormality coefficient ZYX according to the vibration data in this embodiment includes:

[0125] Obtain the vibration speed ZS and the vibration amplitude ZF in the vibration data as well as the standard vibration speed BZS and the standard vibration amplitude BZF;

[0126] When the vibration speed is less than the standard vibration speed, the vibration speed influence value is set to 0; otherwise, the vibration speed influence value is the absolute value ZSY of the difference between the vibration speed and the standard vibration speed; the standard vibration speed is set based on experience, and in this embodiment, BZS is set to 25 mm / s;

[0127] When the vibration amplitude is less than the standard vibration amplitude, the vibration amplitude impact value is set to 0; otherwise, the vibration amplitude impact value is the absolute value ZFY of the difference between the vibration amplitude and the standard vibration amplitude; the standard vibration amplitude is set based on experience;

[0128] The vibration anomaly coefficient ZYX is calculated by the formula ZYX=1-exp(-(α7×ZSY / DS+α8×ZFY / DF)); wherein α7 and α8 are weight coefficients, α7 and α8∈(0,1), and specific values ​​are set according to experience; the greater the vibration velocity influence value, the greater the vibration amplitude influence value, and the more serious the centrifuge vibration anomaly, so the vibration anomaly coefficient increases accordingly.

[0129] This embodiment obtains the equipment wear coefficient based on historical equipment data, and can accurately obtain the equipment abnormality that affects the centrifuge speed. At the same time, the vibration abnormality coefficient is calculated through the vibration data of the centrifuge to obtain the vibration abnormality of the centrifuge. The state of the centrifuge is considered from multiple aspects and the centrifuge abnormality coefficient is calculated accordingly, which provides higher detection accuracy and efficiency for the abnormal state detection of the centrifuge.

[0130] See also Figure 2 In this embodiment, the alarm signal is generated according to the abnormal coefficient of the centrifuge, including:

[0131] Obtain centrifuge abnormality coefficient, equipment wear coefficient and vibration abnormality coefficient;

[0132] Determine whether the centrifuge abnormality coefficient is greater than the equipment abnormality threshold, which is set based on experience; if yes, generate an equipment failure alarm signal;

[0133] No, determine whether the equipment wear coefficient is greater than the wear threshold, which is set based on experience; Yes, generate an equipment wear alarm signal; No, do nothing;

[0134] Determine whether the vibration abnormality coefficient is greater than the vibration threshold, which is set based on experience; if yes, generate an equipment vibration abnormality alarm signal; if no, do nothing.

[0135] See also Figure 3 Another aspect of the present application provides an intelligent control method for centrifuge speed, comprising:

[0136] S0: Get equipment data and material data;

[0137] S1: Input the detection image in the material data into the material category recognition model to obtain the category label; find the initial speed according to the category label and material weight;

[0138] S2: Calculate the equipment wear coefficient according to historical equipment data; calculate the equipment adjustment speed according to the equipment wear coefficient and the initial speed, and assign the equipment adjustment speed to the equipment speed;

[0139] S3: calculating the centrifuge abnormality coefficient after calculating the vibration abnormality coefficient according to the equipment data; generating an alarm signal according to the centrifuge abnormality coefficient;

[0140] S4: Provide prompts based on alarm signals and contact management.

[0141] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0142] The working principle of the present application is as follows: by acquiring equipment data and material data; inputting the detection image in the material data into the material category recognition model to obtain the category label; searching for the initial speed according to the category label and the material weight; calculating the equipment wear coefficient according to the historical equipment data; calculating the equipment adjustment speed according to the equipment wear coefficient and the initial speed, and assigning the equipment adjustment speed to the equipment speed; calculating the centrifuge abnormality coefficient after calculating the vibration abnormality coefficient according to the equipment data; generating an alarm signal according to the centrifuge abnormality coefficient; making a prompt according to the alarm signal and contacting the management personnel, accurately obtaining the equipment parameters of the centrifuge through multivariate data, taking into account the difference in speed caused by equipment wear, dynamically adjusting the centrifuge speed, monitoring the status of the centrifuge in real time, improving the speed control efficiency of the centrifuge, and avoiding the problem that the prior art ignores the influence of equipment wear on the centrifuge when adjusting the centrifuge speed, so that the adjustment speed does not meet the requirements, resulting in low speed control efficiency of the centrifuge.

[0143] The above embodiments are only used to illustrate the technical method of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical method of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present application.

Claims

1. An intelligent control system for centrifuge speed, characterized in that: include: Data acquisition module, data analysis module, control module, early warning module and database; The data acquisition module is used to acquire equipment data and material data through data acquisition equipment; The data analysis module: inputs the detection image in the material data into the material category recognition model to obtain the category label; searches for the initial speed according to the category label and the material weight; calculates the equipment wear coefficient according to the historical equipment data; calculates the equipment adjustment speed according to the equipment wear coefficient and the initial speed; calculates the centrifuge abnormality coefficient after calculating the vibration abnormality coefficient according to the equipment data; generating an alarm signal according to the centrifuge abnormality coefficient; The control module: assigns the device adjustment speed to the device speed; The early warning module: makes prompts according to the alarm signal and contacts the management personnel.

2. An intelligent control system for centrifuge speed according to claim 1, characterized in that: The method of searching for the initial rotation speed according to the category label and the material weight includes: Get the category label and its corresponding material concentration and material weight; Integrate category labels and their corresponding material concentrations and material weights into comprehensive data; The comprehensive data were input into the speed-time prediction model to obtain the initial rotation speed and centrifugation time.

3. An intelligent control system for centrifuge speed according to claim 2, characterized in that: The speed time prediction model is constructed by a neural network model, including: Obtain several historical category labels, material concentrations and material weights and their corresponding equipment speeds and centrifugation times; integrate the historical category labels, material concentrations and material weights into historical comprehensive data; And divide it into training data, verification data and test data according to the equipment rotation speed and centrifugation time; perform data preprocessing on the training data, verification data and test data to obtain the training set, verification set and test set; Select the neural network model as the base model; Train the basic model with the training set, and adjust the learning rate on the validation set to obtain the pre-trained model; By verifying the pre-trained model on the test set, we finally get the input comprehensive data, and the output is the speed-time prediction model of the equipment speed and centrifugal time.

4. The intelligent control system for centrifuge speed according to claim 1, characterized in that: The calculation of the equipment wear coefficient according to the historical equipment data includes: Acquire historical equipment working data and historical equipment environment data in the historical equipment data; the historical equipment working data includes low-load working time DFZi and high-load working time GFZj; the historical equipment environment data includes temperature and humidity under several different load data of the centrifuge equipment; Generate corresponding environmental impact coefficients DHYXi and GHYXj according to the temperature and humidity under several different load data of the centrifuge equipment; The equipment wear coefficient SMX of the centrifuge equipment is calculated by the formula SMX=1-exp(-(α1×∑(DFZi / DT×(1+DHYXi))+α2×∑(GFZj / DT×(1+GHYXj)))); wherein α1 and α2 are weight coefficients, α1 and α2∈(0,1), and α1<α2; DT is the unit time; i represents the number of the low-load working time of the centrifuge equipment, i=1, 2,…, M, and M is the total number of low-load working times; j represents the number of the high-load working time of the centrifuge equipment, j=1, 2,…, N, and N is the total number of high-load working times.

5. The intelligent control system for centrifuge speed according to claim 4, characterized in that: The method of generating corresponding environmental impact coefficients DHYXi and GHYXj according to the temperature and humidity under several different load data of the centrifuge equipment includes: Obtain the working temperatures DWi and DSi corresponding to the low-load working time, the working temperature GWj and working humidity GSj corresponding to the high-load working time, and the optimum working temperature W and the optimum working humidity S; Calculate the temperature influence coefficients DWYXi and GWYXj by the formula; DWYXi=1-exp(-(|DWi-W| / DW)^βw); GWYXj=1-exp(-(|GWj-W| / DW)^βw); Calculate humidity influence coefficients DSYXi and GSYXj by formula; DSYXi=1-exp(-(|DSi-S| / DS)^βs); GSYXj=1-exp(-(|GSj-S| / DS)^βs); Calculate the environmental impact coefficients DHYXi and GHYXj through the formula; DHYXi=α3×DWYXi+α4×DSYXi; GHYXj=α3×GWYXj+α4×GSYXj; wherein α3 and α4 are weight coefficients, α3 and α4∈(0,1); DW is unit temperature, DS is unit humidity, βs and βw are exponential coefficients, βs and βw∈(0,1).

6. The intelligent control system for centrifuge speed according to claim 1, characterized in that: The step of calculating the device adjustment speed according to the device wear coefficient and the initial speed includes: Obtain equipment wear coefficient SMX and initial speed CV; The equipment adjustment speed STV is calculated by the formula STV=CV / (h×(1-SMX^(1+β1)); wherein h is the proportional coefficient, h∈(0,1); and β1 is the exponential coefficient, β1∈(0,1).

7. The intelligent control system for centrifuge speed according to claim 1, characterized in that: The step of calculating the centrifuge abnormality coefficient after calculating the vibration abnormality coefficient according to the equipment data includes: Obtain vibration data and equipment wear coefficient SMX from equipment data; Calculate the vibration abnormality coefficient ZYX based on the vibration data; The centrifuge abnormality coefficient LYX is calculated by the formula LYX=α5×SMX+α6×ZYX; wherein α5 and α6 are weight coefficients, α5 and α6∈(0,1).

8. The intelligent control system for centrifuge speed according to claim 7, characterized in that: The calculation of the vibration abnormality coefficient ZYX according to the vibration data includes: Obtain the vibration speed ZS and the vibration amplitude ZF in the vibration data as well as the standard vibration speed BZS and the standard vibration amplitude BZF; When the vibration speed is less than the standard vibration speed, the vibration speed impact value is set to 0; otherwise, the vibration speed impact value is the absolute value ZSY of the difference between the vibration speed and the standard vibration speed; When the vibration amplitude is less than the standard vibration amplitude, the vibration amplitude impact value is set to 0; otherwise, the vibration amplitude impact value is the absolute value ZFY of the difference between the vibration amplitude and the standard vibration amplitude; The vibration abnormality coefficient ZYX is calculated by the formula ZYX=1-exp(-(α7×ZSY / DS+α8×ZFY / DF)); wherein α7 and α8 are weight coefficients, α7 and α8∈(0,1).

9. The intelligent control system for centrifuge speed according to claim 1, characterized in that: The generating of an alarm signal according to the centrifuge abnormality coefficient comprises: Obtain centrifuge abnormality coefficient, equipment wear coefficient and vibration abnormality coefficient; When the centrifuge abnormality coefficient is greater than the equipment abnormality threshold, an equipment failure alarm signal is generated; Otherwise, determine whether the equipment wear coefficient is greater than the wear threshold, if yes, generate an equipment wear alarm signal; if no, do nothing; Determine whether the vibration abnormality coefficient is greater than the vibration threshold. If yes, generate an equipment vibration abnormality alarm signal; if no, do nothing.

10. An intelligent control method for centrifuge speed, applied to an intelligent control system for centrifuge speed according to any one of claims 1 to 9, characterized in that: include: S0: Get equipment data and material data; S1: Input the detection image in the material data into the material category recognition model to obtain the category label; find the initial speed according to the category label and material weight; S2: Calculate the equipment wear coefficient according to historical equipment data; calculate the equipment adjustment speed according to the equipment wear coefficient and the initial speed, and assign the equipment adjustment speed to the equipment speed; S3: calculating the centrifuge abnormality coefficient after calculating the vibration abnormality coefficient according to the equipment data; generating an alarm signal according to the centrifuge abnormality coefficient; S4: Provide prompts based on alarm signals and contact management.

Images