Glass transmission intelligent differential adjusting system

Abstract

The invention discloses an intelligent differential adjustment system for glass transmission, relates to the technical field of intelligent control, and solves the technical problems that the speed is unstable and cannot be intelligently adjusted, so that produced glass is easy to generate scratches and corrugations, and even the yield of the glass is low in the prior art. The wear coefficient of the corresponding transmission motor is generated according to historical parameter data and historical environment data of the transmission motor; generating an alarm signal according to the wear coefficient; inputting the pre-processed detection image into a quality detection model to obtain a quality label; generating a yield according to the quality label; the adjustment transmission speed of the corresponding transmission motor is generated according to the finished product rate and the corresponding abrasion coefficient, the transmission speed is dynamically adjusted by considering the environmental factors and the abrasion of the transmission motor, and the glass quality problem caused by the fact that the transmission speed is increased due to the fact that a large amount of heat is carried during glass production, and roller table rollers are heated to expand is relieved. And the yield of the glass is improved.

Description

Technical Field

[0001] The present application belongs to the field of intelligent control technology, and specifically is a glass transmission intelligent differential adjustment system. Background Art

[0002] As an important building material and a key component of many industrial products, glass has many functions, influencing factors and a wide range of applications. It is widely used in the fields of construction, electronics, medical care, home furnishings and clothing. The quality of glass greatly affects the user experience and building safety.

[0003] In the process of glass production and processing, the rollers in the roller table near the annealing area of ​​the traditional glass transmission system are easily expanded by heat, which increases the radius of the rollers and then increases the linear speed of the rollers. As a result, the speed of the glass transmission system is different from the moving speed of the glass, making the produced glass prone to scratches and ripples, and even leading to a low glass yield. Therefore, further improvements are still needed to develop an intelligent differential adjustment system to improve the efficiency and quality of glass transmission. Summary of the invention

[0004] 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 a glass transmission intelligent differential adjustment system to solve the technical problems in the prior art that the speed is often unstable and cannot be adjusted intelligently, which makes the produced glass prone to scratches and ripples, and even leads to a low glass yield.

[0005] To achieve the above-mentioned purpose, the first aspect of the present application provides a glass transmission intelligent differential adjustment system, comprising: a data acquisition module, a data analysis module, an early warning module and a database;

[0006] The data acquisition module: sequentially acquires control speeds, parameter data, environmental data and detection images corresponding to a plurality of transmission motors and real-time radius of rollers corresponding to the transmission motors through a data acquisition device;

[0007] The data analysis module: generates a wear coefficient of the corresponding transmission motor according to the historical parameter data and historical environmental data of the transmission motor; generates an alarm signal according to the wear coefficient; inputs the detection image after image preprocessing into the quality detection model to obtain a quality label; generates a yield rate according to the quality label; generates an adjusted transmission speed of the corresponding transmission motor according to the yield rate and the corresponding wear coefficient;

[0008] The early warning module: makes corresponding prompts according to the alarm signal and contacts relevant management personnel.

[0009] The present application generates a wear coefficient of a corresponding transmission motor according to historical parameter data and historical environmental data of the transmission motor; generates an alarm signal according to the wear coefficient; inputs a detection image after image preprocessing into a quality detection model to obtain a quality label; generates a yield rate according to the quality label; generates an adjusted transmission speed of the corresponding transmission motor according to the yield rate and the corresponding wear coefficient; makes corresponding prompts according to the alarm signal, takes environmental factors and the wear of the transmission motor into consideration, and dynamically adjusts the transmission speed according to the wear coefficient and the yield rate, thereby alleviating glass quality problems caused by the fact that the roller of the roller table expands due to heat when the glass is just produced, resulting in an increase in the transmission speed due to the large amount of heat it carries, thereby improving the yield rate of the glass.

[0010] Furthermore, the generating of the wear coefficient of the corresponding transmission motor according to the historical parameter data and the historical environmental data of the transmission motor includes:

[0011] Obtain historical parameter data and historical environmental data; the historical parameter data includes load data and its corresponding working time, no-load working time GZS0i, low-load working time GZS1k, and high-load working time GZS2j; the historical environmental data includes temperature and humidity under several different load data corresponding to the corresponding transmission motor;

[0012] Generate corresponding environmental impact coefficients HYX0i, HYX1k and HYX2j according to the temperature and humidity under several different load data of the corresponding transmission motor;

[0013] Calculate the wear coefficient MX of the corresponding transmission motor through the formula;

[0014] MX=g×arctan(α0×∑(GZS0i / DT×(1+HYX0i))+α1×∑(GZS1k / DT×(1+HYX1k))+α2×∑(GZS2j / DT×(1+HYX2j)));

[0015] Among them, g is the proportional coefficient, g∈(0,2 / π), α0, α1 and α2 are weight coefficients, α0, α1 and α2∈(0,1), and α0<α1<α2; DT is the unit time; i represents the number of the no-load working time of the corresponding transmission motor, i=1, 2,…, M, M is the total number of no-load working time; k represents the number of the low-load working time of the corresponding transmission motor, k=1, 2,…, N, N is the total number of low-load working time; j represents the number of the high-load working time of the corresponding transmission motor, j=1, 2,…, Q, Q is the total number of high-load working time.

[0016] Furthermore, the generation of corresponding environmental impact coefficients HYX0i, HYX1k and HYX2j according to the temperature and humidity under several different load data of the corresponding transmission motor includes:

[0017] Obtain the temperature W0i, W1k, W2j and humidity S0i, S1k, S2j of the corresponding transmission motor under several different load data, as well as the optimum working temperature range and the optimum working humidity range; the optimum working temperature range includes the maximum value WZD of the optimum temperature range and the minimum value WZX of the optimum temperature range; the optimum working humidity range includes the maximum value SZD of the optimum humidity range and the minimum value SZX of the optimum humidity range;

[0018] The optimum temperature intermediate value ZWZ is calculated by the formula ZWZ = (WFD + WFX) / 2;

[0019] The temperature floating deviation WFP is calculated by the formula WFP = (WFD-WFX) / 2;

[0020] The optimum humidity median value ZSZ is calculated by the formula ZWZ = (SFD + SFX) / 2;

[0021] The humidity floating deviation SFP is calculated by the formula WFP = (SFD-SFX) / 2;

[0022] Determine whether the temperature is within the optimum working temperature range;

[0023] Yes, the temperature influence coefficient WYX0i=WYX1k=WYX2j=0;

[0024] No, calculate the temperature influence coefficients WYX0i, WYX1k and WYX2j by the formula;

[0025] WYX0i=gw×arctan(((|W0i-ZWZ|-WFP) / DW)^βw);

[0026] WYX1k=gw×arctan(((|W1k-ZWZ|-WFP) / DW)^βw);

[0027] WYX2j=gw×arctan(((|W2j-ZWZ|-WFP) / DW)^βw);

[0028] Determine whether the humidity is within the optimum working humidity range;

[0029] Yes, humidity influence coefficient SYX0i=SYX1k=SYX2j=0;

[0030] No, calculate the humidity influence coefficients SYX0i, SYX1k and SYX2j by the formula;

[0031] SYX0i=gs×arctan(((|S0i-ZSZ|-SFP) / DS)^βs);

[0032] SYX1k=gs×arctan(((|S1k-ZSZ|-SFP) / DS)^βs);

[0033] SYX2j=gs×arctan(((|S2j-ZSZ|-SFP) / DS)^βs);

[0034] Calculate the environmental impact coefficients HYX0i, HYX1k and HYX2j through the formula;

[0035] HYX0i=α3×WYX0i+α4×SYX0i;

[0036] HYX1k=α3×WYX1k+α4×SYX1k;

[0037] HYX2j=α3×WYX2j+α4×SYX2j;

[0038] Among them, gw and gs are proportional coefficients, gw and gs∈(0, 2 / π); βw and βs are exponential coefficients, βw and βs∈(0, 1); DW is unit temperature, DS is unit humidity; α3 and α4 are weight coefficients, α3 and α4∈(0, 1).

[0039] Further, generating an alarm signal according to the wear coefficient includes:

[0040] Obtain the wear coefficient of each transmission motor;

[0041] Determine whether the wear coefficient is greater than a corresponding wear threshold;

[0042] If yes, a motor failure alarm signal is generated;

[0043] If no, determine whether the wear coefficient is greater than D times the wear threshold; if yes, generate a motor scrap warning signal; if no, do nothing.

[0044] Furthermore, the quality detection model is constructed through an artificial intelligence model, including:

[0045] Acquire a number of historical glass images and their corresponding quality labels; the quality labels include normal labels and defect labels;

[0046] Divide a number of historical glass images and their corresponding quality labels into training data, verification data and test data; perform image preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set;

[0047] Select an AI model as the base model;

[0048] 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;

[0049] By verifying the pre-trained model on the test set, we finally obtain a quality detection model whose input is the detection image and output is the quality label.

[0050] Furthermore, generating the yield rate according to the quality label includes:

[0051] Obtain the number of inspected glasses JS and the number of defective glasses QS whose quality labels are defective labels per unit time;

[0052] Calculate the yield rate CPL through the formula;

[0053] CPL=1-QS / JS.

[0054] Furthermore, the step of generating the adjusted transmission speed of the corresponding transmission motor according to the yield rate and the corresponding wear coefficient includes:

[0055] Step 1: Set the number of the transmission motor to u according to the transmission order of the glass; u = 1, 2, ..., B; B is the total number of transmission motors; obtain the yield rate and the yield rate threshold; determine whether the yield rate is greater than the yield rate threshold; if yes, end the operation; if no, proceed to step 2;

[0056] Step 2: Set the number u of the adjustment drive motor to "1";

[0057] Step 3: Obtain the control speed KV of the adjustment transmission motor numbered "u"; the control speed is the input speed value when the transmission motor is not adjusted;

[0058] Step 4: Obtain the real-time radius r and wear coefficient MX of the roller corresponding to the adjustment transmission motor numbered "u";

[0059] The actual transmission speed V of the transmission motor is adjusted by calculation through a formula; the actual transmission speed V refers to the linear speed of the roller on the roller table after the control speed of the transmission motor is converted by the motor;

[0060] V=k×KV×(1-MX^(1+βv)×r / Dr;

[0061] The transmission speed TV of the transmission motor is adjusted by calculation through the formula;

[0062] TV = V × exp (-k1 × (CPY-CPL)); where k and k1 are proportional coefficients, k and k1∈(0, 1); βv is the exponential coefficient, βv∈(0, 1); Dr is the unit radius;

[0063] Determine whether TV is less than the minimum transmission speed threshold;

[0064] If yes, go to step 5; if no, go to step 6;

[0065] Step 5: Set the transmission speed to the lowest transmission speed threshold; generate the adjustment control speed TKV of the adjustment transmission motor according to the adjustment transmission speed; obtain the adjusted yield rate CPL, and determine whether the yield rate is greater than the yield rate threshold; if yes, end the operation; if no, determine whether u is equal to B; if yes, generate a fault alarm signal; if no, set the number of the adjustment transmission motor to "u=u+1", and enter step 3;

[0066] Step 6: Generate an adjustment control speed TKV for adjusting the transmission motor according to the adjustment transmission speed; obtain the adjusted yield rate CPL, and determine whether the yield rate is greater than the yield rate threshold; if yes, end the operation; if no, KV=TKV, and go to step 4.

[0067] The present application adjusts the transmission speeds corresponding to each transmission motor in sequence according to the glass transmission order based on the yield rate, and when the transmission speed reaches the minimum transmission speed threshold, adjusts the transmission speed of the next transmission motor; the transmission speeds of all transmission motors are taken into consideration in affecting the glass quality, effectively solving the problem of glass quality caused by the transmission speed and improving the glass production efficiency.

[0068] Further, the adjusting control speed TKV of the transmission motor is generated according to the adjusted transmission speed, including:

[0069] Obtain the adjustment of transmission speed TV, the wear coefficient MX of the transmission motor and the real-time radius r of the corresponding roller;

[0070] The adjustment control speed TKV of the transmission motor is adjusted by calculation through the formula;

[0071] TKV=TV / (k×(1-MX^(1+βv)×r / Dr); wherein k is the proportional coefficient, k∈(0,1); βv is the exponential coefficient, βv∈(0,1); and Dr is the unit radius.

[0072] Compared with the prior art, the beneficial effects of this application are:

[0073] 1. The present application generates a wear coefficient of a corresponding transmission motor according to historical parameter data and historical environmental data of the transmission motor; generates an alarm signal according to the wear coefficient; inputs a detection image after image preprocessing into a quality detection model to obtain a quality label; generates a yield rate according to the quality label; generates an adjustment control speed of the corresponding transmission motor according to the yield rate and the corresponding wear coefficient; makes corresponding prompts according to the alarm signal, takes environmental factors and the wear of the transmission motor into consideration, and dynamically adjusts the transmission speed according to the wear coefficient and the yield rate, thereby alleviating glass quality problems caused by the fact that the roller of the roller table expands due to heat when the glass is just produced, which increases the yield rate of the glass.

[0074] 2. The present application adjusts the transmission speeds of each transmission motor in sequence according to the glass transmission order based on the yield rate, and when the transmission speed reaches the minimum transmission speed threshold, adjusts the transmission speed of the next transmission motor; the transmission speeds of all transmission motors are taken into consideration in affecting the glass quality, effectively solving the problem of glass quality caused by transmission speed and improving the glass production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] 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.

[0076] Figure 1 This is a schematic diagram of the principle of the glass transmission intelligent differential adjustment system of this application;

[0077] Figure 2 A method flow chart of the glass transmission intelligent differential adjustment system of the present application;

[0078] Figure 3 Flowchart for adjusting transmission speed for generation of this application. DETAILED DESCRIPTION

[0079] 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.

[0080] See also Figure 1-Figure 2 , the first aspect of the present application provides a glass transmission intelligent differential adjustment system, including: a data acquisition module, a data analysis module, an early warning module and a database;

[0081] Data acquisition module: The control speed, parameter data, environmental data and detection images corresponding to several transmission motors and the real-time radius of the roller corresponding to the transmission motor are obtained in sequence through the data acquisition equipment; the data acquisition equipment includes relevant sensors and high-definition cameras, etc. The control speed is the speed set for the transmission motor, the parameter data includes load data and its corresponding working time, the environmental data is the environmental data around the transmission motor, including temperature and humidity, etc., and the detection image is the detection image of the transmission glass at the end of the transmission motor;

[0082] Data analysis module: Generate the wear coefficient of the corresponding transmission motor according to the historical parameter data and historical environmental data of the transmission motor. The wear coefficient refers to the degree of wear of the transmission motor; generate an alarm signal according to the wear coefficient; input the detection image after image preprocessing into the quality detection model to obtain a quality label; generate the yield rate according to the quality label; generate the adjusted transmission speed of the corresponding transmission motor according to the yield rate and the corresponding wear coefficient. The adjusted transmission speed refers to the speed value to which the transmission motor should be adjusted;

[0083] Early warning module: make corresponding prompts according to the alarm signals and contact relevant management personnel; the alarm signals include motor scrap alarm signal, motor scrap early warning signal and fault alarm signal.

[0084] This embodiment generates a wear coefficient of a corresponding transmission motor according to historical parameter data and historical environmental data of the transmission motor; generates an alarm signal according to the wear coefficient; inputs a detection image after image preprocessing into a quality detection model to obtain a quality label; generates a yield rate according to the quality label; generates an adjusted transmission speed of the corresponding transmission motor according to the yield rate and the corresponding wear coefficient; makes corresponding prompts according to the alarm signal, takes environmental factors and the wear of the transmission motor into consideration, and dynamically adjusts the transmission speed according to the wear coefficient and the yield rate, thereby alleviating glass quality problems caused by the fact that the roller of the roller table expands due to heat when the glass is just produced, resulting in an increase in the transmission speed due to the large amount of heat it carries, thereby improving the yield rate of the glass.

[0085] The wear coefficient of the corresponding transmission motor is generated according to the historical parameter data and historical environmental data of the transmission motor, including:

[0086] Obtain historical parameter data and historical environmental data; historical parameter data includes load data and its corresponding working hours, no-load working hours GZS0i, no-load working hours are working hours when the load of the transmission motor is 0; low-load working hours GZS1k, low-load working hours are working hours when the load is below the load threshold; high-load working hours GZS2j, high-load working hours are working hours when the load is above the load threshold; the load threshold is set according to experience; historical environmental data includes temperature and humidity under several different load data corresponding to the corresponding transmission motor;

[0087] The corresponding environmental impact coefficients HYX0i, HYX1k and HYX2j are generated according to the temperature and humidity under several different load data of the corresponding transmission motor; the environmental impact coefficient refers to the influence degree of environmental data on the wear of the transmission motor;

[0088] Calculate the wear coefficient MX of the corresponding transmission motor through the formula;

[0089] MX=g×arctan(α0×∑(GZS0i / DT×(1+HYX0i))+α1×∑(GZS1k / DT×(1+HYX1k))+α2×∑(GZS2j / DT×(1+HYX2j)));

[0090] Among them, g is the proportional coefficient, g∈(0,2 / π), α0, α1 and α2 are weight coefficients, α0, α1 and α2∈(0,1), and α0<α1<α2; DT is the unit time; i represents the number of the no-load working time of the corresponding transmission motor, i=1, 2,…, M, M is the total number of no-load working time; k represents the number of the low-load working time of the corresponding transmission motor, k=1, 2,…, N, N is the total number of low-load working time; j represents the number of the high-load working time of the corresponding transmission motor, j=1, 2,…, Q, Q is the total number of high-load working time; the damage of high-load working time to the transmission motor is more serious than that of low-load working time and no-load working time. The longer the working time, the more serious the wear of the transmission motor will be, and the environmental data will also have an impact on the damage of the transmission motor in operation; with the increase of load and working time, and the larger the environmental impact coefficient, it means that the transmission motor is more likely to be damaged, so the wear coefficient of the transmission motor will increase accordingly.

[0091] The corresponding environmental impact coefficients HYX0i, HYX1k and HYX2j are generated according to the temperature and humidity under several different load data of the corresponding drive motor, including:

[0092] Obtain the temperature W0i, W1k, W2j and humidity S0i, S1k, S2j of the corresponding transmission motor under several different load data, as well as the optimum working temperature range and the optimum working humidity range; the optimum working temperature range includes the maximum value WZD of the optimum temperature range and the minimum value WZX of the optimum temperature range; the optimum working humidity range includes the maximum value SZD of the optimum humidity range and the minimum value SZX of the optimum humidity range;

[0093] The maximum value of the optimum temperature range refers to the maximum value in the optimum working temperature range, and the minimum value of the optimum temperature range refers to the minimum value in the optimum working temperature range; the maximum value of the optimum humidity range refers to the maximum value in the optimum working humidity range, and the minimum value of the optimum humidity range refers to the minimum value in the optimum working humidity range;

[0094] The optimum temperature intermediate value ZWZ is calculated by the formula ZWZ = (WFD + WFX) / 2;

[0095] The temperature floating deviation WFP is calculated by the formula WFP = (WFD-WFX) / 2; the larger the optimal working temperature range, the greater the temperature floating deviation will be;

[0096] The optimum humidity median value ZSZ is calculated by the formula ZWZ = (SFD + SFX) / 2;

[0097] The humidity floating deviation SFP is calculated by the formula WFP = (SFD-SFX) / 2; the larger the optimal working humidity range, the greater the humidity floating deviation will be;

[0098] Determine whether the temperature is within the optimum working temperature range;

[0099] Yes, the temperature influence coefficient WYX0i=WYX1k=WYX2j=0;

[0100] No, calculate the temperature influence coefficients WYX0i, WYX1k and WYX2j by the formula;

[0101] WYX0i=gw×arctan(((|W0i-ZWZ|-WFP) / DW)^βw);

[0102] WYX1k=gw×arctan(((|W1k-ZWZ|-WFP) / DW)^βw);

[0103] WYX2j=gw×arctan(((|W2j-ZWZ|-WFP) / DW)^βw); The greater the difference between the temperature and the optimum working temperature range, the more the temperature deviates from the optimum working temperature range. The degree of wear of the transmission motor that continues to work in the deviation from the optimum working temperature range will be aggravated, so the temperature anomaly coefficient will increase accordingly;

[0104] Determine whether the humidity is within the optimum working humidity range;

[0105] Yes, humidity influence coefficient SYX0i=SYX1k=SYX2j=0;

[0106] No, calculate the humidity influence coefficients SYX0i, SYX1k and SYX2j by the formula;

[0107] SYX0i=gs×arctan(((|S0i-ZSZ|-SFP) / DS)^βs);

[0108] SYX1k=gs×arctan(((|S1k-ZSZ|-SFP) / DS)^βs);

[0109] SYX2j=gs×arctan(((|S2j-ZSZ|-SFP) / DS)^βs); The greater the difference between humidity and the optimal humidity range, the more the humidity deviates from the optimal humidity range. The degree of wear of the transmission motor that continues to work in the deviation from the optimal humidity range will be aggravated, so the humidity abnormality coefficient increases accordingly;

[0110] Calculate the environmental impact coefficients HYX0i, HYX1k and HYX2j through the formula;

[0111] HYX0i=α3×WYX0i+α4×SYX0i;

[0112] HYX1k=α3×WYX1k+α4×SYX1k;

[0113] HYX2j=α3×WYX2j+α4×SYX2j; As the temperature anomaly coefficient and humidity anomaly coefficient increase, it means that the temperature and humidity are increasingly deviating from the optimal working temperature range and the optimal working humidity range, the environment is becoming worse and worse, the degree of wear of the transmission motor will increase, and therefore the environmental anomaly coefficient will also increase;

[0114] Among them, gw and gs are proportional coefficients, gw and gs∈(0, 2 / π), and the setting of gw and gs is to make the temperature anomaly coefficient and the humidity anomaly coefficient be in the range of 0 to 1, and the specific values ​​of gw and gs are set according to experience; βw and βs are exponential coefficients, βw and βs∈(0, 1), and the specific values ​​are set according to experience; DW is unit temperature, DS is unit humidity, and the specific values ​​are set according to experience. In this embodiment, DW is set to 1°C and DS is set to 1%; α3 and α4 are weight coefficients, α3 and α4∈(0, 1), and the specific values ​​are set according to experience.

[0115] Generates alarm signals based on wear factors, including:

[0116] Obtain the wear coefficient of each transmission motor;

[0117] Determine whether the wear coefficient is greater than the corresponding wear threshold; the wear threshold is set based on experience;

[0118] If yes, a motor failure alarm signal is generated;

[0119] No, determine whether the wear coefficient is greater than D times the wear threshold; Yes, generate a motor scrap warning signal; No, do nothing; D is a proportional coefficient, which is set based on experience. In this embodiment, D is set to 0.7.

[0120] The quality inspection model is built through an artificial intelligence model, including:

[0121] Obtain several historical glass images and their corresponding quality labels; the quality labels include normal labels and defect labels; the normal labels and defect labels are evaluated and marked by experts;

[0122] Several historical glass images and their corresponding quality labels are divided into training data, verification data and test data; image preprocessing is performed 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;

[0123] Select an artificial intelligence model as the basic model; the artificial intelligence model includes a convolutional neural network model, etc.;

[0124] 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;

[0125] By verifying the pre-trained model on the test set, we finally obtain a quality detection model whose input is the detection image and output is the quality label.

[0126] Generate yields based on quality labels, including:

[0127] Obtain the number of inspected glasses JS and the number of defective glasses with quality labels as defects QS within a unit time; the unit time is set based on experience and can be set to 1 hour or 1 day;

[0128] Calculate the yield rate CPL through the formula;

[0129] CPL = 1-QS / JS; when the number of inspected glasses per unit time remains unchanged, as the number of defective glasses with defective quality labels decreases, the product yield will increase accordingly.

[0130] See also Figure 3 , according to the yield rate and the corresponding wear coefficient, the adjusted transmission speed of the corresponding transmission motor is generated, including:

[0131] Step 1: Set the number of the transmission motor to u according to the transmission order of the glass; u = 1, 2, ..., B; B is the total number of transmission motors; obtain the yield rate and the yield rate threshold; determine whether the yield rate is greater than the yield rate threshold; if yes, end the operation; if no, proceed to step 2;

[0132] Step 2: Set the number u of the adjustment drive motor to "1";

[0133] Step 3: Obtain the control speed KV of the adjustment transmission motor numbered "u"; the control speed is the input speed value when the transmission motor is not adjusted;

[0134] Step 4: Obtain the real-time radius r and wear coefficient MX of the roller corresponding to the adjustment transmission motor numbered "u"; the real-time radius is the radius value of the roller in the roller table corresponding to the transmission motor at different stages. When transmitting high-temperature glass, the roller in the roller table will expand due to the high temperature, resulting in an increase in the real-time radius;

[0135] The actual transmission speed V of the transmission motor is adjusted by calculation through the formula; the actual transmission speed V refers to the linear speed of the roller on the roller table after the control speed of the transmission motor is converted by the motor;

[0136] V=k×KV×(1-MX^(1+βv)×r / Dr); When the control speed is not adjusted and the wear coefficient remains unchanged, the angular velocity of the roller on the roller table due to the control speed remains unchanged, while the transmission of high-temperature glass will cause the roller of the roller table to expand due to heat, resulting in an increase in the real-time radius of the roller, which in turn increases the linear velocity of the roller, thereby increasing the actual transmission speed;

[0137] The transmission speed TV of the transmission motor is adjusted by calculation through the formula;

[0138] TV=V×exp(-k1×(CPY-CPL)); When the yield rate does not reach the yield rate threshold, it is necessary to reduce the actual transmission speed corresponding to the transmission motor to reduce factors such as glass scratches caused by too fast speed or product failure caused by insufficient annealing time. The lower the yield rate, the greater the reduction in the actual transmission speed. Therefore, the adjusted transmission speed should also be reduced, and then the adjusted transmission speed is reduced accordingly; wherein, k and k1 are proportional coefficients, k and k1∈(0,1), and the specific values ​​are set according to experience; βv is an exponential coefficient, βv∈(0,1), and the specific value is set according to experience; Dr is a unit radius, which is set according to experience. In this embodiment, Dr is set to 1 cm;

[0139] Determine whether TV is less than the minimum transmission speed threshold; the minimum transmission speed threshold is the minimum transmission speed set to ensure the production efficiency of glass transmission. The annealing treatment effect of glass transmitted at this speed is completely feasible. Once it is lower than this speed, the transmission efficiency of the glass is very low, which seriously affects the production process. The specific value is set based on experience;

[0140] If yes, go to step 5; if no, go to step 6;

[0141] Step 5: Set the transmission speed to the lowest transmission speed threshold; generate the adjustment control speed TKV of the transmission motor according to the adjustment transmission speed; obtain the adjusted yield rate CPL, and determine whether the yield rate is greater than the yield rate threshold; if yes, end the operation; if no, determine whether u is equal to B; if yes, generate a fault alarm signal. This step is to detect that when the yield rate of all transmission motors is still less than the yield rate threshold after adjustment, an alarm signal needs to be issued to carefully check the entire glass production transmission process; if no, set the number of the transmission motor to "u=u+1" and enter step 3;

[0142] Step 6: Generate an adjustment control speed TKV for adjusting the transmission motor according to the adjusted transmission speed; obtain the adjusted yield rate CPL, and determine whether the yield rate is greater than the yield rate threshold; if yes, end the operation; if no, KV=TKV, and go to step 4. This step is to continue to adjust the current transmission motor so that the actual transmission speed reaches the minimum transmission speed.

[0143] This embodiment adjusts the transmission speeds corresponding to each transmission motor in sequence according to the glass transmission order based on the yield rate, and when the transmission speed reaches the minimum transmission speed threshold, adjusts the transmission speed of the next transmission motor; the transmission speeds of all transmission motors are taken into consideration in affecting the glass quality, effectively solving the problem of glass quality caused by the transmission speed and improving the glass production efficiency.

[0144] Generate an adjustment control speed TKV of the adjustment transmission motor according to the adjustment transmission speed, including:

[0145] Obtain the adjustment of transmission speed TV, the wear coefficient MX of the transmission motor and the real-time radius r of the corresponding roller;

[0146] The adjustment control speed TKV of the transmission motor is adjusted by calculation through the formula;

[0147] TKV=TV / (k×(1-MX^(1+βv)×r / Dr); once the transmission speed is adjusted, the corresponding control speed is also determined; where k is the proportional coefficient, k∈(0,1); βv is the exponential coefficient, βv∈(0,1); and Dr is the unit radius.

[0148] 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.

[0149] The working principle of the present application is as follows: by obtaining the control speeds, parameter data, environmental data and detection images corresponding to several transmission motors and the real-time radius of the roller corresponding to the transmission motor; generating the wear coefficient of the corresponding transmission motor according to the historical parameter data and historical environmental data of the transmission motor; generating an alarm signal according to the wear coefficient; inputting the detection image after image preprocessing into the quality detection model to obtain a quality label; generating the yield rate according to the quality label; generating the adjusted transmission speed of the corresponding transmission motor according to the yield rate and the corresponding wear coefficient; making corresponding prompts according to the alarm signal, and contacting relevant management personnel, taking environmental factors and the wear of the transmission motor into consideration, and dynamically adjusting the transmission speed according to the wear coefficient and the yield rate, thereby reducing the glass quality problem caused by the roller table roller expanding due to the large amount of heat when the glass is just produced, thereby improving the glass yield rate.

[0150] 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. Glass transmission intelligent differential adjustment system, characterized by: include: Data collection module, data analysis module, early warning module and database; The data acquisition module: sequentially acquires control speeds, parameter data, environmental data and detection images corresponding to a plurality of transmission motors and real-time radius of rollers corresponding to the transmission motors through a data acquisition device; The data analysis module: generates a wear coefficient of the corresponding transmission motor according to the historical parameter data and historical environmental data of the transmission motor; generates an alarm signal according to the wear coefficient; inputs the detection image after image preprocessing into the quality detection model to obtain a quality label; generates a yield rate according to the quality label; generates an adjusted transmission speed of the corresponding transmission motor according to the yield rate and the corresponding wear coefficient; The early warning module: makes corresponding prompts according to the alarm signal and contacts relevant management personnel.

2. The glass transmission intelligent differential adjustment system according to claim 1 is characterized in that: The step of generating the wear coefficient of the corresponding transmission motor according to the historical parameter data and the historical environmental data of the transmission motor comprises: Obtain historical parameter data and historical environmental data; the historical parameter data includes load data and its corresponding working time, no-load working time GZS0i, low-load working time GZS1k, and high-load working time GZS2j; the historical environmental data includes temperature and humidity under several different load data corresponding to the corresponding transmission motor; Generate corresponding environmental impact coefficients HYX0i, HYX1k and HYX2j according to the temperature and humidity under several different load data of the corresponding transmission motor; Calculate the wear coefficient MX of the corresponding transmission motor through the formula; MX=g×arctan(α0×∑(GZS0i / DT×(1+HYX0i))+α1×∑(GZS1k / DT×(1+HYX1k))+α2×∑(GZS2j / DT×(1+HYX2j))); Among them, g is the proportional coefficient, g∈(0,2 / π), α0, α1 and α2 are weight coefficients, α0, α1 and α2∈(0,1), and α0<α1<α2; DT is the unit time; i represents the number of the no-load working time of the corresponding transmission motor, i=1, 2,…, M, M is the total number of no-load working time; k represents the number of the low-load working time of the corresponding transmission motor, k=1, 2,…, N, N is the total number of low-load working time; j represents the number of the high-load working time of the corresponding transmission motor, j=1, 2,…, Q, Q is the total number of high-load working time.

3. The glass transmission intelligent differential adjustment system according to claim 2 is characterized in that: The corresponding environmental impact coefficients HYX0i, HYX1k and HYX2j are generated according to the temperature and humidity under several different load data of the corresponding transmission motor, including: Obtain the temperature W0i, W1k, W2j and humidity S0i, S1k, S2j of the corresponding transmission motor under several different load data, as well as the optimum working temperature range and the optimum working humidity range; the optimum working temperature range includes the maximum value WZD of the optimum temperature range and the minimum value WZX of the optimum temperature range; the optimum working humidity range includes the maximum value SZD of the optimum humidity range and the minimum value SZX of the optimum humidity range; The optimum temperature intermediate value ZWZ is calculated by the formula ZWZ = (WFD + WFX) / 2; The temperature floating deviation WFP is calculated by the formula WFP = (WFD-WFX) / 2; The optimum humidity median value ZSZ is calculated by the formula ZWZ = (SFD + SFX) / 2; The humidity floating deviation SFP is calculated by the formula WFP = (SFD-SFX) / 2; Determine whether the temperature is within the optimum working temperature range; Yes, the temperature influence coefficient WYX0i=WYX1k=WYX2j=0; No, calculate the temperature influence coefficients WYX0i, WYX1k and WYX2j by the formula; WYX0i=gw×arctan(((|W0i-ZWZ|-WFP) / DW)^βw); WYX1k=gw×arctan(((|W1k-ZWZ|-WFP) / DW)^βw); WYX2j=gw×arctan(((|W2j-ZWZ|-WFP) / DW)^βw); Determine whether the humidity is within the optimum working humidity range; Yes, humidity influence coefficient SYX0i=SYX1k=SYX2j=0; No, calculate the humidity influence coefficients SYX0i, SYX1k and SYX2j by the formula; SYX0i=gs×arctan(((|S0i-ZSZ|-SFP) / DS)^βs); SYX1k=gs×arctan(((|S1k-ZSZ|-SFP) / DS)^βs); SYX2j=gs×arctan(((|S2j-ZSZ|-SFP) / DS)^βs); Calculate the environmental impact coefficients HYX0i, HYX1k and HYX2j through the formula; HYX0i=α3×WYX0i+α4×SYX0i; HYX1k=α3×WYX1k+α4×SYX1k; HYX2j=α3×WYX2j+α4×SYX2j; Among them, gw and gs are proportional coefficients, gw and gs∈(0, 2 / π); βw and βs are exponential coefficients, βw and βs∈(0, 1); DW is unit temperature, DS is unit humidity; α3 and α4 are weight coefficients, α3 and α4∈(0, 1).

4. The glass transmission intelligent differential adjustment system according to claim 1, characterized in that: The generating of an alarm signal according to the wear coefficient comprises: Obtain the wear coefficient of each transmission motor; Determine whether the wear coefficient is greater than a corresponding wear threshold; If yes, a motor failure alarm signal is generated; If no, determine whether the wear coefficient is greater than D times the wear threshold; if yes, generate a motor scrap warning signal; if no, do nothing.

5. The glass transmission intelligent differential adjustment system according to claim 1, characterized in that: The quality inspection model is constructed through an artificial intelligence model, including: Acquire a number of historical glass images and their corresponding quality labels; the quality labels include normal labels and defect labels; Divide a number of historical glass images and their corresponding quality labels into training data, verification data and test data; perform image preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set; Select an AI model as the base model; 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; By verifying the pre-trained model on the test set, we finally obtain a quality detection model whose input is the detection image and output is the quality label.

6. The glass transmission intelligent differential adjustment system according to claim 1, characterized in that: The step of generating the adjusted transmission speed of the corresponding transmission motor according to the yield rate and the corresponding wear coefficient includes: Step 1: Set the number of the transmission motor to u according to the transmission order of the glass; u = 1, 2, ..., B; B is the total number of transmission motors; obtain the yield rate and the yield rate threshold; determine whether the yield rate is greater than the yield rate threshold; if yes, end the operation; if no, proceed to step 2; Step 2: Set the number u of the adjustment drive motor to "1"; Step 3: Obtain the control speed KV of the transmission motor numbered "u"; the control speed is the input speed value when the transmission motor is not adjusted; Step 4: Obtain the real-time radius r and wear coefficient MX of the roller corresponding to the adjustment transmission motor numbered "u"; The actual transmission speed V of the transmission motor is adjusted by calculation through a formula; the actual transmission speed V refers to the linear speed of the roller on the roller table after the control speed of the transmission motor is converted by the motor; V=k×KV×(1-MX^(1+βv)×r / Dr; The transmission speed TV of the transmission motor is adjusted by calculation through the formula; TV = V × exp (-k1 × (CPY-CPL)); where k and k1 are proportional coefficients, k and k1∈(0, 1); βv is the exponential coefficient, βv∈(0, 1); Dr is the unit radius; Determine whether TV is less than the minimum transmission speed threshold; If yes, go to step 5; if no, go to step 6; Step 5: Set the transmission speed to the lowest transmission speed threshold; generate the adjustment control speed TKV of the transmission motor according to the adjustment transmission speed; obtain the adjusted yield rate CPL, and determine whether the yield rate is greater than the yield rate threshold; if yes, end the operation; if no, determine whether u is equal to B; if yes, generate a fault alarm signal; if no, set the number of the transmission motor to "u=u+1" and enter step 3; Step 6: Generate an adjustment control speed TKV for adjusting the transmission motor according to the adjustment transmission speed; obtain the adjusted yield rate CPL, and determine whether the yield rate is greater than the yield rate threshold; if yes, end the operation; if no, KV=TKV, and go to step 4.

7. The glass transmission intelligent differential adjustment system according to claim 6, characterized in that: The step of generating an adjustment control speed TKV of the adjustment transmission motor according to the adjustment transmission speed comprises: Obtain the adjustment of transmission speed TV, the wear coefficient MX of the transmission motor and the real-time radius r of the corresponding roller; The adjustment control speed TKV of the transmission motor is adjusted by calculation through the formula; TKV=TV / (k×(1-MX^(1+βv)×r / Dr); wherein k is the proportional coefficient, k∈(0,1); βv is the exponential coefficient, βv∈(0,1); and Dr is the unit radius.

Images