Adaptive Optimization Control System of Temperature and Pressure Curve of Multilayer Ceramic Lamination Equipment

Abstract

The present invention belongs to the technical field of temperature and pressure control, and discloses an adaptive optimization control system for temperature and pressure curves of multilayer ceramic lamination equipment; the control system comprises: a data acquisition module, which is used to acquire influencing data before the start of multilayer ceramic lamination; a data analysis module, which is used to analyze the influencing data and obtain an optimal temperature curve and an optimal pressure curve; a law acquisition module, which is used to obtain the law of linkage change of temperature and pressure during the multilayer ceramic lamination process; an optimization control module, which is used to optimize the optimal temperature curve and the optimal pressure curve according to the law of linkage change of temperature and pressure during the multilayer ceramic lamination process, and perform multilayer ceramic lamination according to the optimized optimal temperature curve and the optimal pressure curve; the present invention can realize high-precision matching control of temperature and pressure; greatly improve the quality stability of laminated products, reduce the scrap rate, and provide sustainable technical means for increasing production capacity and saving production costs.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature and pressure control, and more specifically to a temperature and pressure curve adaptive optimization control system for multilayer ceramic lamination equipment. Background Art

[0002] Multilayer ceramic lamination equipment is one of the key equipment for producing high-performance ceramic materials. Multilayer ceramic lamination equipment laminates multiple ceramic sheets together and sinters them under high temperature and high pressure conditions to prepare ceramic products with excellent mechanical properties and thermal stability. During the lamination process, controlling the temperature and pressure curves is crucial to obtaining high-quality ceramic products.

[0003] The temperature and pressure control system of traditional multilayer ceramic lamination equipment usually uses a fixed temperature and pressure curve to control the working process of the lamination equipment; however, due to the characteristics of ceramic materials and changes in process conditions, the fixed temperature and pressure curve is often difficult to adapt to different production requirements, resulting in unstable product quality or failure to meet design requirements, thereby increasing the scrap rate;

[0004] Of course, there are also intelligent temperature and pressure adaptive control methods. For example, the patent with publication number CN117348423A discloses an adaptive neural network control method, device, and equipment for temperature and pressure of a cremator; including: calculating the tracking error value of the real-time temperature and pressure parameters in the cremator according to the temperature and pressure expected trajectory function; performing data mining on historical combustion data to obtain an empirical knowledge model; using the empirical knowledge model to query the system estimated initial value; using the pre-configured parameter adaptive estimation law to perform parameter estimation on the tracking error value according to the system estimated initial value to obtain an estimated parameter vector; using the neural network controller after the estimated parameter vector parameters are adjusted to generate a temperature and pressure control instruction; using the supervisory control service after parameter configuration to generate a supervisory temperature and pressure control instruction, and calculating the instruction difference between the temperature and pressure control instruction and the supervisory temperature and pressure control instruction; when the instruction difference is less than the conditional threshold, temperature control is performed according to the temperature and pressure control instruction; this invention can improve the accuracy and response speed of the cremator voltage regulation;

[0005] However, the above technology estimates the temperature and pressure parameters according to the real-time temperature and pressure parameters through the expected trajectory function and the empirical knowledge model. If it is used in a multilayer ceramic stacking device, the temperature and pressure will affect each other during the operation of the multilayer ceramic stacking device; that is, the change of one data will cause the change of the other data; therefore, when optimizing the temperature and pressure curve, it is necessary to consider the actual coupling relationship between temperature and pressure, but the above technology does not involve the law of linkage change between temperature and pressure;

[0006] In view of this, the present invention proposes a temperature-pressure curve adaptive optimization control system for a multilayer ceramic lamination device to solve the above-mentioned problem. Summary of the invention

[0007] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solution: a temperature and pressure curve adaptive optimization control system for a multilayer ceramic lamination device, comprising:

[0008] A data acquisition module is used to collect the impact data before the multi-layer ceramic lamination begins;

[0009] Data analysis module, used to analyze the influencing data and obtain the best temperature curve and the best pressure curve;

[0010] A law acquisition module is used to obtain the linkage change law of temperature and pressure during the multilayer ceramic lamination process;

[0011] The optimization control module is used to optimize the optimal temperature curve and the optimal pressure curve according to the linkage change law of temperature and pressure during the multi-layer ceramic stacking process, and perform multi-layer ceramic stacking according to the optimized optimal temperature curve and optimal pressure curve.

[0012] Further, the impact data includes temperature impact data and pressure impact data;

[0013] The temperature impact data includes the number of ceramic layers, the first attribute data, and the ambient temperature value;

[0014] The number of ceramic layers is the total number of ceramic layers to be laminated;

[0015] The first attribute data includes m groups of ceramic physical data, where m is the number of ceramic layers and m is an integer greater than 1, and one group of ceramic physical data corresponds to a piece of ceramic; the ceramic physical data is the physical data of the ceramic before lamination; the ceramic physical data includes thermal conductivity and density;

[0016] The ambient temperature value is the temperature value of the environment where the ceramic lamination equipment is located;

[0017] The pressure impact data includes the number of ceramic layers, second attribute data and ambient humidity value;

[0018] The second attribute data includes m′ groups of ceramic structure data, m=m′, wherein one group of ceramic structure data corresponds to a piece of ceramic; the ceramic structure data is the structure data of the ceramic before lamination; the ceramic structure data includes hardness and thickness;

[0019] The environmental humidity value is the humidity value of the environment where the ceramic lamination equipment is located.

[0020] Furthermore, the method for acquiring the ceramic physical data is as follows: using an RFID reader to read the RFID tag embedded in the ceramic surface, obtaining the corresponding tag ID information, sending the tag ID information to a ceramic database, and obtaining a set of ceramic physical data corresponding to the tag ID information, wherein the RFID tag corresponds to the tag ID information one-to-one, and the tag ID information corresponds to the ceramic physical data one-to-one; the ceramic database records the ceramic physical data corresponding to each tag ID information;

[0021] The method for acquiring the ceramic structure data is consistent with the method for acquiring the ceramic physical data.

[0022] Furthermore, the method for obtaining the optimal temperature curve includes:

[0023] Calculate the initial temperature based on the temperature influence data;

[0024] Q temperature curves are preset, where Q is an integer greater than 1;

[0025] According to the initial temperature, select from Q temperature curves temperature curves and construct a temperature curve set;

[0026] According to the temperature impact data, the best temperature curve is selected from the temperature curve set.

[0027] The calculation method of the initial temperature includes:

[0028]

[0029]

[0030] Where, T c is the initial temperature, TC is the number of ceramic layers, SS1 is the first property coefficient, T h is the ambient temperature, RD i is the thermal conductivity of the i-th group of ceramic physical data, MD i is the density in the i-th group of ceramic physical data, ω1, ω2, ω3 are preset weight coefficients, i∈[1,m].

[0031] The method for constructing the temperature curve set includes:

[0032] Obtain the starting temperature in Q temperature curves, where the starting temperature is the temperature value corresponding to the starting point in the temperature curve; sort the starting temperatures of the Q temperature curves from large to small to generate a sorting table, add the initial temperature to the sorting table, count the number of starting temperatures before the initial temperature in the sorting table, and mark it as a first number D, count the number of starting temperatures after the initial temperature, and mark it as a second number D′;

[0033] like Then select the D starting temperatures before the initial temperature and the D starting temperatures after the initial temperature. The starting temperature;

[0034] like Then select the D′ starting temperatures after the initial temperature and the D′ starting temperatures before the initial temperature. The starting temperature;

[0035] like and Then filter out the The starting temperature, and the The starting temperature;

[0036] A starting temperature set is constructed according to the screened starting temperatures; and a temperature curve set is constructed according to the temperature curves corresponding to the starting temperatures in the starting temperature set.

[0037] Furthermore, the method for selecting the best temperature curve from the temperature curve set includes:

[0038] Step a: Preset initialization temperature T max , minimum temperature T min , cooling coefficient δ and maximum number of iterations And let the current temperature T = T max ;

[0039] Step b: randomly set a feasible solution χ, the feasible solution χ is the temperature curve, the temperature curve range is the temperature curve set, and the temperature curve range is the range of the feasible solution χ;

[0040] Step c: determine the fitness function;

[0041] The expression of fitness function is: f = ZL;

[0042] In the formula, f is the fitness, ZL is the stacking quality;

[0043] The lamination quality is the quality of the product obtained after laminating the ceramics according to the temperature curve under the condition of temperature influence data;

[0044] Step d: Calculate the fitness f corresponding to the feasible solution χ; take the feasible solution χ as the current point, perform random perturbations in the neighborhood of the current point, obtain a new feasible solution χ′, and calculate the fitness f′ corresponding to the new feasible solution χ′;

[0045] Step e: Calculate the fitness difference f″, the expression of the fitness difference f″ is f″=f′-f;

[0046] If the fitness difference f″>0, let χ=χ′, that is, assign the value of the new feasible solution χ′ to the feasible solution χ; if the fitness difference f″≤0, calculate the probability p′, and let χ=χ′ according to the probability p′; the expression of probability p′ is: In the formula, e is a natural constant;

[0047] Step f: Repeat steps d to e until the number of loops reaches the maximum number of iterations. When , the loop ends and enters step g;

[0048] Step g: Set the current temperature T = T × δ, that is, cool down the current temperature in step a, and assign the value after cooling to the current temperature; set the maximum number of iterations The value of the maximum number of iterations after the reduction is assigned to the maximum number of iterations;

[0049] Step h: Repeat steps d to g until the current temperature T < T min When , the cycle ends, and the temperature curve corresponding to the feasible solution χ is obtained and used as the optimal temperature curve.

[0050] Furthermore, the method for obtaining the stacking quality includes:

[0051] The temperature curve and temperature influence data corresponding to the feasible solution χ are used as analysis data; the analysis data are input into the trained quality prediction model to predict the corresponding stacking quality;

[0052] The training process of the quality prediction model includes:

[0053] Pre-collect N groups of analysis data corresponding to the stacking qualities, and convert the analysis data and the corresponding stacking qualities into a corresponding set of feature vectors;

[0054] Each group of feature vectors is used as the input of the quality prediction model. The quality prediction model takes a group of overlay qualities corresponding to each group of analysis data as output, and takes the actual overlay quality corresponding to each group of analysis data as the prediction target, and the actual overlay quality is the overlay quality corresponding to the analysis data collected in advance; minimizing the sum of prediction errors of all analysis data is used as the training target; the quality prediction model is trained until the sum of prediction errors converges and the training is stopped; the quality prediction model is a deep neural network model.

[0055] Furthermore, the method for obtaining the optimal pressure curve includes:

[0056] Calculate the initial pressure based on the pressure impact data;

[0057] M pressure curves are preset, where M is an integer greater than 1;

[0058] According to the initial pressure, select from M pressure curves pressure curves and construct a pressure curve set; the method for constructing the pressure curve set is the same as the method for constructing the temperature curve set;

[0059] According to the pressure influence data, the best pressure curve is selected from the pressure curve set; the method of selecting the best pressure curve from the pressure curve set is consistent with the method of selecting the best temperature curve from the temperature curve set.

[0060] Furthermore, the calculation method of the initial pressure includes:

[0061] P c =ψ1×TC+ψ2×SS2+ψ3×H;

[0062]

[0063] Where P c is the initial pressure, SS2 is the second property coefficient, H is the ambient humidity value, YD j is the hardness of the jth group of ceramic structure data, HD j is the thickness in the jth group of ceramic structure data, ψ1, ψ2, ψ3 are preset proportional coefficients, j∈[1,m′].

[0064] Furthermore, the method for obtaining the linkage change law of temperature and pressure during the multilayer ceramic lamination process includes:

[0065] Step 1: Match Q temperature curves to M pressure curves one by one, Q=M; calculate the temperature mean corresponding to each temperature curve and the pressure mean corresponding to each pressure curve in turn, and the temperature mean and the pressure mean also correspond one by one; take a temperature mean and the corresponding pressure mean as a set of analysis sets;

[0066] Step 2: Construct a function set, which includes linear functions and nonlinear functions;

[0067] Step 3: Randomly select a function that is not marked as a selected function from the function set, and mark it as a selected function, and randomly select q groups of analysis sets, Q>q>0; substitute the q groups of analysis sets into the selected function, and calculate the function expression of the selected function, in which the temperature mean is used as the independent variable and the pressure mean is used as the dependent variable; then substitute the temperature mean in the unselected analysis set into the function expression of the selected function, calculate the corresponding pressure mean, and mark it as the calculated pressure mean, and the calculated pressure mean corresponds to the pressure mean in the unselected analysis set one by one; subtract the corresponding pressure mean from each calculated pressure mean to obtain the pressure error; add each pressure error obtained in turn and divide it by the number of pressure errors to obtain the error mean;

[0068] Step 4: Loop step 3 until each function in the function set obtains the corresponding error mean, and the loop ends; sort each error mean from large to small, and use the function expression corresponding to the last error mean as the linkage change law of temperature and pressure during the multilayer ceramic lamination process.

[0069] Furthermore, the step of optimizing the optimal temperature curve and the optimal pressure curve includes:

[0070] Step A: marking the function expression corresponding to the linkage change law of temperature and pressure in the multilayer ceramic lamination process as a calculation formula; calculating the pressure curve corresponding to the optimal temperature curve according to the calculation formula, and marking it as an evaluation pressure curve;

[0071] Step B: Calculate the sum of the pressure errors between the evaluation pressure curve and the optimal pressure curve, where the sum of the pressure errors is the area between the evaluation pressure curve and the optimal pressure curve;

[0072] Step C: preset an error threshold, and compare the total pressure error with the error threshold;

[0073] If the sum of the pressure errors is greater than the error threshold, the pressure drop gradient is calculated using the chain rule, the optimal pressure curve is optimized according to the pressure drop gradient, and the optimal pressure curve is replaced with the optimized optimal pressure curve;

[0074] If the sum of the pressure errors is less than or equal to the error threshold, the optimal pressure curve is not optimized;

[0075] Step D: Calculate the temperature curve corresponding to the optimal pressure curve according to the calculation formula and mark it as the evaluation temperature curve;

[0076] Step E: Calculate the total temperature error between the evaluation temperature curve and the optimal temperature curve, where the total temperature error is the area between the evaluation temperature curve and the optimal temperature curve;

[0077] Step F: Compare the total temperature error with the error threshold;

[0078] If the sum of the temperature errors is greater than the error threshold, the chain rule is used to calculate the temperature drop gradient, the optimal temperature curve is optimized according to the temperature drop gradient, and the optimal temperature curve is replaced with the optimized optimal temperature curve;

[0079] If the sum of the temperature errors is less than or equal to the error threshold, the optimal temperature curve is not optimized;

[0080] Step G: looping steps A to F until the sum of the pressure errors and the sum of the temperature errors are both less than or equal to the error threshold, the loop ends, and the optimized optimal temperature curve and optimal pressure curve are obtained.

[0081] The technical effects and advantages of the temperature and pressure curve adaptive optimization control system of the multilayer ceramic lamination equipment of the present invention are as follows:

[0082] By collecting various influencing data before ceramic lamination, the optimal temperature and pressure curve is preliminarily obtained after analysis; and the linkage change law of temperature and pressure in the lamination process is identified. According to this actual coupling relationship, the optimal temperature and pressure curve is adaptively optimized; the temperature and pressure are controlled according to the optimized optimal temperature and pressure curve; compared with a single fixed curve, it can truly reflect the changes in various conditions, thereby achieving high-precision matching control of temperature and pressure; it greatly improves the quality stability of laminated products, reduces the scrap rate, realizes intelligent production, and provides a sustainable technical means to increase production capacity and save production costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] Figure 1 Schematic diagram of a temperature-pressure curve adaptive optimization control system for a multilayer ceramic lamination device according to Example 1 of the present invention;

[0084] Figure 2 This is a flow chart of a method for adaptively optimizing the temperature and pressure curves of a multilayer ceramic lamination device according to Embodiment 2 of the present invention;

[0085] Figure 3 This is a schematic diagram of an electronic device according to Embodiment 3 of the present invention;

[0086] Figure 4 This is a schematic diagram of a storage medium according to Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0087] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0088] Embodiment 1:

[0089] See also Figure 1 As shown, the temperature-pressure curve adaptive optimization control system of the multilayer ceramic lamination equipment described in this embodiment includes a data acquisition module, a data analysis module, a law acquisition module and an optimization control module; each module is connected by wired and / or wireless means to realize data transmission between modules;

[0090] A data acquisition module is used to collect the impact data before the multi-layer ceramic lamination begins;

[0091] The impact data include temperature impact data and pressure impact data;

[0092] Temperature impact data include the number of ceramic layers, first attribute data, and ambient temperature value;

[0093] The number of ceramic layers is the total number of ceramic layers to be laminated; the method for obtaining the number of ceramic layers is as follows: a photoelectric sensor is installed in the moving path of the pressing plate in the ceramic laminating equipment. When the pressing plate presses down on the ceramic, the pressing plate will drop, causing the photoelectric sensor to generate an electrical pulse signal. The number of electrical pulse signals is counted to obtain the number of ceramic layers; the more ceramic layers there are, the greater the thickness that heat energy needs to penetrate and conduct, and the longer it takes for the inner layer to obtain heat. In order to shorten the time it takes for the inner layer to reach temperature, a higher temperature is required during the ceramic laminating process, and vice versa;

[0094] The first attribute data includes m groups of ceramic physical data, where m is the number of ceramic layers, and m is an integer greater than 1, and one group of ceramic physical data corresponds to a piece of ceramic; the ceramic physical data is the physical data of the ceramic before lamination; the ceramic physical data includes thermal conductivity and density; the greater the thermal conductivity and density, the faster the heat conduction speed of the ceramic, the stronger the heat absorption capacity, and the lower the temperature required in the ceramic lamination process, and vice versa;

[0095] The method for acquiring ceramic physical data is as follows: using an RFID reader to read the RFID tag embedded in the ceramic surface, obtaining the corresponding tag ID information, sending the tag ID information to a ceramic database, and obtaining a set of ceramic physical data corresponding to the tag ID information, wherein the RFID tag corresponds to the tag ID information one-to-one, and the tag ID information corresponds to the ceramic physical data one-to-one; the ceramic database records the ceramic physical data corresponding to the tag ID information of each ceramic, and when the ceramic is produced, the corresponding RFID tag is embedded in the surface of each ceramic;

[0096] The ambient temperature value is the temperature value of the environment where the ceramic lamination equipment is located; the ambient temperature value is obtained by a temperature sensor installed in the environment where the ceramic lamination equipment is located; the higher the ambient temperature value, the higher the temperature of the ceramic itself before lamination, and the lower the temperature required during the ceramic lamination process, and vice versa;

[0097] Pressure impact data include the number of ceramic layers, second attribute data and ambient humidity value;

[0098] The second attribute data includes m′ groups of ceramic structure data, m=m′, where one group of ceramic structure data corresponds to a piece of ceramic; the ceramic structure data is the structure data of the ceramic before lamination; the ceramic structure data includes hardness and thickness; the method for obtaining the ceramic structure data is consistent with the method for obtaining the ceramic physical data; the greater the hardness, the greater the difficulty of the ceramic to bear the force, and the greater the pressure needs to be applied to complete the deformation and bonding of the ceramic, and vice versa; the greater the thickness, in order to ensure that the ceramic is fully laminated, a greater equivalent stress needs to be applied, that is, a greater pressure needs to be applied, and vice versa;

[0099] The ambient humidity value is the humidity value of the environment where the ceramic lamination equipment is located; the ambient humidity value is obtained by the humidity sensor installed in the environment where the ceramic lamination equipment is located; the higher the ambient humidity value, the greater the surface tension of the ceramic surface, and the weaker the bonding strength of the ceramic, so more pressure needs to be applied, and vice versa;

[0100] Data analysis module, used to analyze the influencing data and obtain the best temperature curve and the best pressure curve;

[0101] Methods for obtaining the best temperature curve include:

[0102] Calculate the initial temperature based on the temperature influence data;

[0103] The calculation method of initial temperature includes:

[0104]

[0105]

[0106] Where, T c is the initial temperature, TC is the number of ceramic layers, SS1 is the first property coefficient, T h is the ambient temperature, RD i is the thermal conductivity of the i-th group of ceramic physical data, MD i is the density in the i-th group of ceramic physical data, ω1, ω2, ω3 are preset weight coefficients, i∈[1,m];

[0107] The specific value of the weight coefficient in the formula can be set according to the actual situation. The weight coefficient reflects the influence of the temperature influence data on the initial temperature in the ceramic lamination process. Those skilled in the art can preset the corresponding weight coefficient according to the actual influence of the temperature influence data on the initial temperature in the ceramic lamination process, so as to accurately obtain the initial temperature in the ceramic lamination process; since the initial temperature is calculated based on a variety of related influencing parameters, the calculation of the initial temperature is a dimensionless calculation;

[0108] Q temperature curves are preset, where Q is an integer greater than 1. The Q temperature curves are obtained by a technician in this field, during the normal operation of the historical ceramic lamination equipment, using a thermocouple temperature sensor to collect the temperature during the Q ceramic lamination processes, and plotting a curve of multiple temperature values ​​collected during each ceramic lamination process to obtain Q temperature curves;

[0109] According to the initial temperature, select from Q temperature curves temperature curves and construct a temperature curve set;

[0110] The method for constructing a temperature curve set includes:

[0111] Obtain the starting temperature in Q temperature curves, where the starting temperature is the temperature value corresponding to the starting point in the temperature curve; sort the starting temperatures of the Q temperature curves from large to small to generate a sorting table, add the initial temperature to the sorting table, count the number of starting temperatures before the initial temperature in the sorting table, and mark it as a first number D, count the number of starting temperatures after the initial temperature, and mark it as a second number D′;

[0112] like Then select the D starting temperatures before the initial temperature and the D starting temperatures after the initial temperature. The starting temperature;

[0113] like Then select the D′ starting temperatures after the initial temperature and the D′ starting temperatures before the initial temperature. The starting temperature;

[0114] like and Then filter out the The starting temperature, and the The starting temperature;

[0115] Constructing a starting temperature set according to the screened starting temperatures; constructing a temperature curve set according to the temperature curves corresponding to the starting temperatures in the starting temperature set;

[0116] According to the temperature impact data, the best temperature curve is selected from the temperature curve set;

[0117] The steps of selecting the best temperature curve from the temperature curve set include:

[0118] Step a: Preset initialization temperature T max , minimum temperature T min , cooling coefficient δ and maximum number of iterations And let the current temperature T = T max ;

[0119] Step b: randomly set a feasible solution χ, the feasible solution χ is the temperature curve, the temperature curve range is the temperature curve set, and the temperature curve range is the range of the feasible solution χ;

[0120] Step c: determine the fitness function;

[0121] The expression of fitness function is: f = ZL;

[0122] In the formula, f is the fitness, ZL is the stacking quality;

[0123] The lamination quality is the quality of the product obtained after laminating the ceramics according to the temperature curve under the condition of temperature influence data;

[0124] Methods for obtaining the overlay quality include:

[0125] The temperature curve and temperature influence data corresponding to the feasible solution χ are used as analysis data; the analysis data are input into the trained quality prediction model to predict the corresponding stacking quality;

[0126] The specific training process of the quality prediction model includes:

[0127] Pre-collect N groups of analysis data corresponding to the stacking qualities, and convert the analysis data and the corresponding stacking qualities into a corresponding set of feature vectors;

[0128] Each set of feature vectors is used as the input of the quality prediction model. The quality prediction model takes a set of stacking qualities corresponding to each set of analysis data as output, and takes the actual stacking quality corresponding to each set of analysis data as the prediction target. The actual stacking quality is the stacking quality corresponding to the analysis data collected in advance. The training target is to minimize the sum of the prediction errors of all analysis data. The calculation formula of the prediction error is Z K =(α K -μ K ) 2 , where Z K is the prediction error, K is the group number of the eigenvector corresponding to the analysis data, α K is the overlay quality corresponding to the Kth group of analysis data, μ K is the actual stacking quality corresponding to the Kth group of analysis data; the quality prediction model is trained until the sum of the prediction errors reaches convergence and the training is stopped;

[0129] The above-mentioned quality prediction model is specifically a deep neural network model;

[0130] It should be noted that the lamination quality corresponding to the analysis data is obtained by a technician in the field. In the historical ceramic lamination process, multiple sets of different temperature influence data are collected. Under the condition of each set of temperature influence data, ceramic lamination is performed according to Q temperature curves. According to actual experience, the quality of multiple products obtained after ceramic lamination is evaluated, and corresponding evaluation scores are assigned. The evaluation score of each product is used as the lamination quality corresponding to the corresponding analysis data; quality evaluation, for example, evaluates the molding shape, bonding strength, material properties, etc. of the product;

[0131] Step d: Calculate the fitness f corresponding to the feasible solution χ; take the feasible solution χ as the current point, perform random perturbations in the neighborhood of the current point, obtain a new feasible solution χ′, and calculate the fitness f′ corresponding to the new feasible solution χ′;

[0132] Step e: Calculate the fitness difference f″, the expression of the fitness difference f″ is f″=f′-f;

[0133] If the fitness difference f″>0, let χ=χ′, that is, assign the value of the new feasible solution χ′ to the feasible solution χ; if the fitness difference f″≤0, calculate the probability p′, and let χ=χ′ according to the probability p′; the expression of probability p′ is: In the formula, e is a natural constant;

[0134] Step f: Repeat steps d to e until the number of loops reaches the maximum number of iterations. When , the loop ends and enters step g;

[0135] Step g: Set the current temperature T = T × δ, that is, cool down the current temperature in step a, and assign the value after cooling to the current temperature; set the maximum number of iterations That is, assign the value of the maximum number of iterations after the reduction to the maximum number of iterations; if the maximum number of iterations after the reduction is not an integer, the maximum number of iterations after the reduction is rounded up so that the maximum number of iterations after the reduction is an integer;

[0136] Step h: Repeat steps d to g until the current temperature T < T min When , the cycle ends, and the temperature curve corresponding to the feasible solution χ is obtained and used as the optimal temperature curve;

[0137] It should be noted that the initialization temperature T max , minimum temperature T min , cooling coefficient δ and maximum number of iterations As preset parameters, the preset parameters are collected by a technician in this field during the historical ceramic lamination process. For the same temperature influence data, multiple sets of different preset parameters are pre-set in sequence, and the temperature curve is obtained by using the simulated annealing algorithm in sequence. The corresponding fitness is calculated in sequence according to the obtained multiple temperature curves, and the preset parameters corresponding to the temperature curve with the maximum fitness are used as the preset parameters corresponding to the group of temperature influence data. The preset parameters corresponding to multiple sets of different temperature influence data are obtained by analogy, and the mean values ​​of multiple preset parameters (i.e., the initialization temperature mean, the minimum temperature mean, the cooling coefficient mean, and the maximum number of iterations mean) are used as the preset initialization temperature T preset in step a. max , minimum temperature T min , cooling coefficient δ and maximum number of iterations ;

[0138] Methods for obtaining the best pressure curve include:

[0139] Calculate the initial pressure based on the pressure impact data;

[0140] The calculation method of initial pressure includes:

[0141] P c =ψ1×TC+ψ2×SS2+ψ3×H;

[0142]

[0143] Where P c is the initial pressure, SS2 is the second property coefficient, H is the ambient humidity value, YD j is the hardness of the jth group of ceramic structure data, HD j is the thickness in the jth group of ceramic structure data, ψ1, ψ2, ψ3 are preset proportional coefficients, j∈[1,m′];

[0144] The specific value of the proportionality coefficient in the formula can be set according to the actual situation. The proportionality coefficient reflects the influence of the pressure influence data on the initial pressure in the ceramic lamination process. Those skilled in the art can preset the corresponding proportionality coefficient according to the actual influence of the pressure influence data on the initial pressure in the ceramic lamination process, so as to accurately obtain the initial pressure in the ceramic lamination process; since the initial pressure is calculated based on a variety of related influencing parameters, the calculation of the initial pressure is a dimensionless calculation;

[0145] M pressure curves are preset, where M is an integer greater than 1. The M pressure curves are obtained by a technician in the field, during the normal operation of the historical ceramic lamination equipment, using a pressure sensor to collect the pressure during the M ceramic lamination processes, and plotting a curve for multiple pressure values ​​collected during each ceramic lamination process to obtain the M pressure curves;

[0146] According to the initial pressure, select from M pressure curves pressure curves and construct a pressure curve set; the method for constructing the pressure curve set is the same as the method for constructing the temperature curve set;

[0147] According to the pressure influence data, the best pressure curve is selected from the pressure curve set; the method of selecting the best pressure curve from the pressure curve set is consistent with the method of selecting the best temperature curve from the temperature curve set;

[0148] A law acquisition module is used to obtain the linkage change law of temperature and pressure during the multilayer ceramic lamination process;

[0149] The steps of obtaining the linkage variation law of temperature and pressure during the multilayer ceramic lamination process include:

[0150] Step 1: Match Q temperature curves to M pressure curves one by one, Q=M; calculate the temperature mean corresponding to each temperature curve and the pressure mean corresponding to each pressure curve in turn, and the temperature mean and the pressure mean also correspond one by one; take a temperature mean and the corresponding pressure mean as a set of analysis sets;

[0151] Step 2: Construct a function set, which includes linear functions and nonlinear functions. Nonlinear functions include logarithmic functions, exponential functions, power functions, sigmoid functions, etc.

[0152] Step 3: Randomly select a function that is not marked as a selected function from the function set, and mark it as a selected function, and randomly select q groups of analysis sets, Q>q>0; substitute the q groups of analysis sets into the selected function, and calculate the function expression of the selected function, in which the temperature mean is used as the independent variable and the pressure mean is used as the dependent variable; then substitute the temperature mean in the unselected analysis set into the function expression of the selected function, calculate the corresponding pressure mean, and mark it as the calculated pressure mean, and the calculated pressure mean corresponds to the pressure mean in the unselected analysis set one by one; subtract the corresponding pressure mean from each calculated pressure mean to obtain the pressure error; add each pressure error obtained in turn and divide it by the number of pressure errors to obtain the error mean;

[0153] Step 4: loop step 3 until each function in the function set obtains the corresponding error mean, and the loop ends; sort each error mean from large to small, and use the function expression corresponding to the last error mean as the linkage change law of temperature and pressure in the multilayer ceramic lamination process;

[0154] An optimization control module is used to optimize the optimal temperature curve and the optimal pressure curve according to the linkage change law of temperature and pressure during the multi-layer ceramic lamination process, and perform multi-layer ceramic lamination according to the optimized optimal temperature curve and optimal pressure curve;

[0155] The steps for optimizing the optimal temperature curve and the optimal pressure curve include:

[0156] Step A: marking the function expression corresponding to the linkage change law of temperature and pressure in the multilayer ceramic lamination process as a calculation formula; calculating the pressure curve corresponding to the optimal temperature curve according to the calculation formula, and marking it as an evaluation pressure curve;

[0157] Step B: Calculate the sum of the pressure errors between the evaluation pressure curve and the optimal pressure curve. The sum of the pressure errors is the area between the evaluation pressure curve and the optimal pressure curve. It can be directly calculated and obtained using software such as OpenCV and Matlab.

[0158] Step C: preset an error threshold, and compare the total pressure error with the error threshold;

[0159] If the sum of the pressure errors is greater than the error threshold, the pressure drop gradient is calculated using the chain rule, the optimal pressure curve is optimized according to the pressure drop gradient, and the optimal pressure curve is replaced with the optimized optimal pressure curve; the chain rule is a prior art and will not be described in detail here;

[0160] If the sum of the pressure errors is less than or equal to the error threshold, the optimal pressure curve is not optimized;

[0161] Step D: Calculate the temperature curve corresponding to the optimal pressure curve according to the calculation formula and mark it as the evaluation temperature curve;

[0162] Step E: Calculate the total temperature error between the evaluation temperature curve and the optimal temperature curve. The total temperature error is the area between the evaluation temperature curve and the optimal temperature curve. It can be directly calculated and obtained using software such as OpenCV and Matlab.

[0163] Step F: Compare the total temperature error with the error threshold;

[0164] If the sum of the temperature errors is greater than the error threshold, the chain rule is used to calculate the temperature drop gradient, the optimal temperature curve is optimized according to the temperature drop gradient, and the optimal temperature curve is replaced with the optimized optimal temperature curve;

[0165] If the sum of the temperature errors is less than or equal to the error threshold, the optimal temperature curve is not optimized;

[0166] Step G: looping steps A to F until the sum of the pressure error and the sum of the temperature error are both less than or equal to the error threshold, the loop ends, and the optimized best temperature curve and the best pressure curve are obtained;

[0167] It should be noted that the error threshold is determined by a person skilled in the art. In the historical ceramic lamination process, under multiple groups of different influencing data conditions, multiple different curve sets are obtained, each curve set includes an optimal temperature curve and an optimal pressure curve. For the same curve set, steps A to F are cycled, and when each cycle of steps A to F is completed, ceramic lamination is performed according to the obtained optimal temperature curve and optimal pressure curve, and the lamination quality is evaluated until the lamination quality reaches convergence and the cycle ends; since the error threshold has not yet been determined, there is no need to compare the sum of pressure errors and the sum of temperature errors with the error threshold during the cycle; the sum of pressure errors corresponding to the best lamination quality among multiple lamination qualities is marked as the optimal pressure error, and the sum of temperature errors corresponding to the best lamination quality among multiple lamination qualities is marked as the optimal temperature error; and so on, the optimal pressure error and the optimal temperature error corresponding to multiple different curve sets are obtained; the mean of multiple optimal pressure errors is taken as the first mean, the mean of multiple optimal temperature errors is taken as the second mean, and the mean of the first mean and the second mean is taken as the error threshold;

[0168] This embodiment collects various influencing data before ceramic lamination, and preliminarily obtains the optimal temperature and pressure curve after analysis; and identifies the linkage change law of temperature and pressure in the lamination process, and according to this actual coupling relationship, adaptively optimizes the optimal temperature and pressure curve; performs temperature and pressure control according to the optimized optimal temperature and pressure curve; compared with a single fixed curve, it can truly reflect the changes in various conditions, thereby achieving high-precision matching control of temperature and pressure; greatly improves the quality stability of laminated products, reduces the scrap rate, realizes intelligent production, and provides a sustainable technical means for increasing production capacity and saving production costs.

[0169] Embodiment 2:

[0170] See also Figure 2 As shown, the part not described in detail in this embodiment is described in Example 1, and a method for adaptively optimizing and controlling a temperature and pressure curve of a multilayer ceramic lamination device is provided, the method comprising:

[0171] Collect impact data before multi-layer ceramic lamination begins;

[0172] Analyze the influencing data to obtain the best temperature curve and the best pressure curve;

[0173] Obtain the linkage variation law of temperature and pressure during the lamination process of multilayer ceramics;

[0174] According to the linkage variation law of temperature and pressure in the process of multi-layer ceramic lamination, the optimal temperature curve and the optimal pressure curve are optimized, and the multi-layer ceramic lamination is carried out according to the optimized optimal temperature curve and the optimal pressure curve.

[0175] Further, the impact data includes temperature impact data and pressure impact data;

[0176] The temperature impact data includes the number of ceramic layers, the first attribute data, and the ambient temperature value;

[0177] The number of ceramic layers is the total number of ceramic layers to be laminated;

[0178] The first attribute data includes m groups of ceramic physical data, where m is the number of ceramic layers and m is an integer greater than 1, and one group of ceramic physical data corresponds to a piece of ceramic; the ceramic physical data is the physical data of the ceramic before lamination; the ceramic physical data includes thermal conductivity and density;

[0179] The ambient temperature value is the temperature value of the environment where the ceramic lamination equipment is located;

[0180] The pressure impact data includes the number of ceramic layers, second attribute data and ambient humidity value;

[0181] The second attribute data includes m′ groups of ceramic structure data, m=m′, wherein one group of ceramic structure data corresponds to a piece of ceramic; the ceramic structure data is the structure data of the ceramic before lamination; the ceramic structure data includes hardness and thickness;

[0182] The environmental humidity value is the humidity value of the environment where the ceramic lamination equipment is located.

[0183] Furthermore, the method for acquiring the ceramic physical data is as follows: using an RFID reader to read the RFID tag embedded in the ceramic surface, obtaining the corresponding tag ID information, sending the tag ID information to a ceramic database, and obtaining a set of ceramic physical data corresponding to the tag ID information, wherein the RFID tag corresponds to the tag ID information one-to-one, and the tag ID information corresponds to the ceramic physical data one-to-one; the ceramic database records the ceramic physical data corresponding to each tag ID information;

[0184] The method for acquiring the ceramic structure data is consistent with the method for acquiring the ceramic physical data.

[0185] Furthermore, the method for obtaining the optimal temperature curve includes:

[0186] Calculate the initial temperature based on the temperature influence data;

[0187] Q temperature curves are preset, where Q is an integer greater than 1;

[0188] According to the initial temperature, select from Q temperature curves temperature curves and construct a temperature curve set;

[0189] According to the temperature impact data, the best temperature curve is selected from the temperature curve set.

[0190] The calculation method of the initial temperature includes:

[0191]

[0192]

[0193] Where, T c is the initial temperature, TC is the number of ceramic layers, SS1 is the first property coefficient, T h is the ambient temperature, RD i is the thermal conductivity of the i-th group of ceramic physical data, MD i is the density in the i-th group of ceramic physical data, ω1, ω2, ω3 are preset weight coefficients, i∈[1,m].

[0194] The method for constructing the temperature curve set includes:

[0195] Obtain the starting temperature in Q temperature curves, where the starting temperature is the temperature value corresponding to the starting point in the temperature curve; sort the starting temperatures of the Q temperature curves from large to small to generate a sorting table, add the initial temperature to the sorting table, count the number of starting temperatures before the initial temperature in the sorting table, and mark it as a first number D, count the number of starting temperatures after the initial temperature, and mark it as a second number D′;

[0196] like Then select the D starting temperatures before the initial temperature and the D starting temperatures after the initial temperature. The starting temperature;

[0197] like Then select the D′ starting temperatures after the initial temperature and the D′ starting temperatures before the initial temperature. The starting temperature;

[0198] like and Then filter out the The starting temperature, and the The starting temperature;

[0199] A starting temperature set is constructed according to the screened starting temperatures; and a temperature curve set is constructed according to the temperature curves corresponding to the starting temperatures in the starting temperature set.

[0200] Furthermore, the method for selecting the best temperature curve from the temperature curve set includes:

[0201] Step a: Preset initialization temperature T max , minimum temperature Tmin , cooling coefficient δ and maximum number of iterations And let the current temperature T = T max ;

[0202] Step b: randomly set a feasible solution χ, the feasible solution χ is the temperature curve, the temperature curve range is the temperature curve set, and the temperature curve range is the range of the feasible solution χ;

[0203] Step c: determine the fitness function;

[0204] The expression of fitness function is: f = ZL;

[0205] In the formula, f is the fitness, ZL is the stacking quality;

[0206] The lamination quality is the quality of the product obtained after laminating the ceramics according to the temperature curve under the condition of temperature influence data;

[0207] Step d: Calculate the fitness f corresponding to the feasible solution χ; take the feasible solution χ as the current point, perform random perturbations in the neighborhood of the current point, obtain a new feasible solution χ′, and calculate the fitness f′ corresponding to the new feasible solution χ′;

[0208] Step e: Calculate the fitness difference f″, the expression of the fitness difference f″ is f″=f′-f;

[0209] If the fitness difference f″>0, let χ=χ′, that is, assign the value of the new feasible solution χ′ to the feasible solution χ; if the fitness difference f″≤0, calculate the probability p′, and let χ=χ′ according to the probability p′; the expression of probability p′ is: In the formula, e is a natural constant;

[0210] Step f: Repeat steps d to e until the number of loops reaches the maximum number of iterations. When , the loop ends and enters step g;

[0211] Step g: Set the current temperature T = T × δ, that is, cool down the current temperature in step a, and assign the value after cooling to the current temperature; set the maximum number of iterations The value of the maximum number of iterations after the reduction is assigned to the maximum number of iterations;

[0212] Step h: Repeat steps d to g until the current temperature T < T min When , the cycle ends, and the temperature curve corresponding to the feasible solution χ is obtained and used as the optimal temperature curve.

[0213] Furthermore, the method for obtaining the stacking quality includes:

[0214] The temperature curve and temperature influence data corresponding to the feasible solution χ are used as analysis data; the analysis data are input into the trained quality prediction model to predict the corresponding stacking quality;

[0215] The training process of the quality prediction model includes:

[0216] Pre-collect N groups of analysis data corresponding to the stacking qualities, and convert the analysis data and the corresponding stacking qualities into a corresponding set of feature vectors;

[0217] Each group of feature vectors is used as the input of the quality prediction model. The quality prediction model takes a group of overlay qualities corresponding to each group of analysis data as output, and takes the actual overlay quality corresponding to each group of analysis data as the prediction target, and the actual overlay quality is the overlay quality corresponding to the analysis data collected in advance; minimizing the sum of prediction errors of all analysis data is used as the training target; the quality prediction model is trained until the sum of prediction errors converges and the training is stopped; the quality prediction model is a deep neural network model.

[0218] Furthermore, the method for obtaining the optimal pressure curve includes:

[0219] Calculate the initial pressure based on the pressure impact data;

[0220] M pressure curves are preset, where M is an integer greater than 1;

[0221] According to the initial pressure, select from M pressure curves pressure curves and construct a pressure curve set; the method for constructing the pressure curve set is the same as the method for constructing the temperature curve set;

[0222] According to the pressure influence data, the best pressure curve is selected from the pressure curve set; the method of selecting the best pressure curve from the pressure curve set is consistent with the method of selecting the best temperature curve from the temperature curve set.

[0223] Furthermore, the calculation method of the initial pressure includes:

[0224] P c =ψ1×TC+ψ2×SS2+ψ3×H;

[0225]

[0226] Where P c is the initial pressure, SS2 is the second property coefficient, H is the ambient humidity value, YD j is the hardness of the jth group of ceramic structure data, HD j is the thickness in the jth group of ceramic structure data, ψ1, ψ2, ψ3 are preset proportional coefficients, j∈[1,m′].

[0227] Furthermore, the method for obtaining the linkage change law of temperature and pressure during the multilayer ceramic lamination process includes:

[0228] Step 1: Match Q temperature curves to M pressure curves one by one, Q=M; calculate the temperature mean corresponding to each temperature curve and the pressure mean corresponding to each pressure curve in turn, and the temperature mean and the pressure mean also correspond one by one; take a temperature mean and the corresponding pressure mean as a set of analysis sets;

[0229] Step 2: Construct a function set, which includes linear functions and nonlinear functions;

[0230] Step 3: Randomly select a function that is not marked as a selected function from the function set, and mark it as a selected function, and randomly select q groups of analysis sets, Q>q>0; substitute the q groups of analysis sets into the selected function, and calculate the function expression of the selected function, in which the temperature mean is used as the independent variable and the pressure mean is used as the dependent variable; then substitute the temperature mean in the unselected analysis set into the function expression of the selected function, calculate the corresponding pressure mean, and mark it as the calculated pressure mean, and the calculated pressure mean corresponds to the pressure mean in the unselected analysis set one by one; subtract the corresponding pressure mean from each calculated pressure mean to obtain the pressure error; add each pressure error obtained in turn and divide it by the number of pressure errors to obtain the error mean;

[0231] Step 4: Loop step 3 until each function in the function set obtains the corresponding error mean, and the loop ends; sort each error mean from large to small, and use the function expression corresponding to the last error mean as the linkage change law of temperature and pressure during the multilayer ceramic lamination process.

[0232] Furthermore, the step of optimizing the optimal temperature curve and the optimal pressure curve includes:

[0233] Step A: marking the function expression corresponding to the linkage change law of temperature and pressure in the multilayer ceramic lamination process as a calculation formula; calculating the pressure curve corresponding to the optimal temperature curve according to the calculation formula, and marking it as an evaluation pressure curve;

[0234] Step B: Calculate the sum of the pressure errors between the evaluation pressure curve and the optimal pressure curve, where the sum of the pressure errors is the area between the evaluation pressure curve and the optimal pressure curve;

[0235] Step C: preset an error threshold, and compare the total pressure error with the error threshold;

[0236] If the sum of the pressure errors is greater than the error threshold, the pressure drop gradient is calculated using the chain rule, the optimal pressure curve is optimized according to the pressure drop gradient, and the optimal pressure curve is replaced with the optimized optimal pressure curve;

[0237] If the sum of the pressure errors is less than or equal to the error threshold, the optimal pressure curve is not optimized;

[0238] Step D: Calculate the temperature curve corresponding to the optimal pressure curve according to the calculation formula and mark it as the evaluation temperature curve;

[0239] Step E: Calculate the total temperature error between the evaluation temperature curve and the optimal temperature curve, where the total temperature error is the area between the evaluation temperature curve and the optimal temperature curve;

[0240] Step F: Compare the total temperature error with the error threshold;

[0241] If the sum of the temperature errors is greater than the error threshold, the chain rule is used to calculate the temperature drop gradient, the optimal temperature curve is optimized according to the temperature drop gradient, and the optimal temperature curve is replaced with the optimized optimal temperature curve;

[0242] If the sum of the temperature errors is less than or equal to the error threshold, the optimal temperature curve is not optimized;

[0243] Step G: looping steps A to F until the sum of the pressure errors and the sum of the temperature errors are both less than or equal to the error threshold, the loop ends, and the optimized optimal temperature curve and optimal pressure curve are obtained.

[0244] Embodiment 3:

[0245] See also Figure 3 As shown, according to another aspect of the present application, an electronic device 500 is also provided. The electronic device 500 may include one or more processors and one or more memories. The memories store computer readable codes, and when the computer readable codes are run by one or more processors, the temperature-pressing curve adaptive optimization control method of the multilayer ceramic lamination device as described above can be executed.

[0246] The method or system according to the embodiment of the present application can also be used by Figure 3 The electronic device architecture shown in FIG. Figure 3As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, ROM 503, RAM 504, a communication port 505 connected to a network, an input / output 506, a hard disk 507, etc. The storage device in the electronic device 500, such as ROM 503 or hard disk 507, may store the temperature-pressure curve adaptive optimization control method of the multilayer ceramic stacking device provided in the present application. Furthermore, the electronic device 500 may also include a user interface 508. Of course, Figure 3 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 3 One or more components of an electronic device are shown.

[0247] Embodiment 4:

[0248] See also Figure 4 As shown, it is a computer-readable storage medium 600 according to an embodiment of the present application. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are executed by the processor, the temperature-pressure curve adaptive optimization control method of the multilayer ceramic stacking device according to the embodiment of the present application described with reference to the above figures can be executed. The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0249] In addition, according to the embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, which stores machine-readable instructions, and the machine-readable instructions can be executed by a processor to execute instructions corresponding to the method steps provided in the present application, for example: a temperature and pressure curve adaptive optimization control method for a multilayer ceramic lamination device. When the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are executed.

[0250] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0251] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A temperature and pressure curve adaptive optimization control system for multilayer ceramic lamination equipment, characterized in that: include: A data acquisition module is used to collect the impact data before the multi-layer ceramic lamination begins; Data analysis module, used to analyze the influencing data and obtain the best temperature curve and the best pressure curve; The law acquisition module is used to obtain the law of linkage change of temperature and pressure during the multi-layer ceramic lamination process; the method for obtaining the law of linkage change of temperature and pressure during the multi-layer ceramic lamination process includes: Step 1: Match Q temperature curves to M pressure curves one by one, Q=M; calculate the temperature mean corresponding to each temperature curve and the pressure mean corresponding to each pressure curve in turn, and the temperature mean and the pressure mean also correspond one by one; take a temperature mean and the corresponding pressure mean as a set of analysis sets; Step 2: Construct a function set, which includes linear functions and nonlinear functions; Step 3: Randomly select a function that is not marked as a selected function from the function set, and mark it as a selected function, and randomly select q groups of analysis sets, Q>q>0; substitute the q groups of analysis sets into the selected function, and calculate the function expression of the selected function, in which the temperature mean is used as the independent variable and the pressure mean is used as the dependent variable; then substitute the temperature mean in the unselected analysis set into the function expression of the selected function, calculate the corresponding pressure mean, and mark it as the calculated pressure mean, and the calculated pressure mean corresponds to the pressure mean in the unselected analysis set one by one; subtract the corresponding pressure mean from each calculated pressure mean to obtain the pressure error; add each pressure error obtained in turn and divide it by the number of pressure errors to obtain the error mean; Step 4: loop step 3 until each function in the function set obtains the corresponding error mean, and the loop ends; sort each error mean from large to small, and use the function expression corresponding to the last error mean as the linkage change law of temperature and pressure in the multilayer ceramic lamination process; The optimization control module is used to optimize the optimal temperature curve and the optimal pressure curve according to the linkage change law of temperature and pressure during the multi-layer ceramic lamination process, and perform multi-layer ceramic lamination according to the optimized optimal temperature curve and optimal pressure curve; the step of optimizing the optimal temperature curve and the optimal pressure curve includes: Step A: marking the function expression corresponding to the linkage change law of temperature and pressure in the multilayer ceramic lamination process as a calculation formula; calculating the pressure curve corresponding to the optimal temperature curve according to the calculation formula, and marking it as an evaluation pressure curve; Step B: Calculate the sum of the pressure errors between the evaluation pressure curve and the optimal pressure curve, where the sum of the pressure errors is the area between the evaluation pressure curve and the optimal pressure curve; Step C: preset an error threshold, and compare the total pressure error with the error threshold; If the sum of the pressure errors is greater than the error threshold, the pressure drop gradient is calculated using the chain rule, the optimal pressure curve is optimized according to the pressure drop gradient, and the optimal pressure curve is replaced with the optimized optimal pressure curve; If the sum of the pressure errors is less than or equal to the error threshold, the optimal pressure curve is not optimized; Step D: Calculate the temperature curve corresponding to the optimal pressure curve according to the calculation formula and mark it as the evaluation temperature curve; Step E: Calculate the total temperature error between the evaluation temperature curve and the optimal temperature curve, where the total temperature error is the area between the evaluation temperature curve and the optimal temperature curve; Step F: Compare the total temperature error with the error threshold; If the sum of the temperature errors is greater than the error threshold, the chain rule is used to calculate the temperature drop gradient, the optimal temperature curve is optimized according to the temperature drop gradient, and the optimal temperature curve is replaced with the optimized optimal temperature curve; If the sum of the temperature errors is less than or equal to the error threshold, the optimal temperature curve is not optimized; Step G: looping steps A to F until the sum of the pressure errors and the sum of the temperature errors are both less than or equal to the error threshold, the loop ends, and the optimized optimal temperature curve and optimal pressure curve are obtained.

2. The temperature and pressure curve adaptive optimization control system of the multilayer ceramic lamination equipment according to claim 1 is characterized in that: The impact data include temperature impact data and pressure impact data; The temperature impact data includes the number of ceramic layers, the first attribute data, and the ambient temperature value; The number of ceramic layers is the total number of ceramic layers to be laminated; The first attribute data includes m groups of ceramic physical data, where m is the number of ceramic layers and m is an integer greater than 1, and one group of ceramic physical data corresponds to a piece of ceramic; the ceramic physical data is the physical data of the ceramic before lamination; the ceramic physical data includes thermal conductivity and density; The ambient temperature value is the temperature value of the environment where the ceramic lamination equipment is located; The pressure impact data includes the number of ceramic layers, second attribute data and ambient humidity value; The second attribute data includes m′ groups of ceramic structure data, m=m′, wherein one group of ceramic structure data corresponds to a piece of ceramic; the ceramic structure data is the structure data of the ceramic before lamination; the ceramic structure data includes hardness and thickness; The environmental humidity value is the humidity value of the environment where the ceramic lamination equipment is located.

3. The temperature and pressure curve adaptive optimization control system of the multilayer ceramic lamination equipment according to claim 2 is characterized in that: The method for acquiring ceramic physical data comprises: using an RFID reader to read the RFID tag embedded on the ceramic surface, obtaining the corresponding tag ID information, sending the tag ID information to a ceramic database, and obtaining a set of ceramic physical data corresponding to the tag ID information, wherein the RFID tag corresponds to the tag ID information one-to-one, and the tag ID information corresponds to the ceramic physical data one-to-one; the ceramic database records the ceramic physical data corresponding to each tag ID information; The method for acquiring the ceramic structure data is consistent with the method for acquiring the ceramic physical data.

4. The temperature and pressure curve adaptive optimization control system of the multilayer ceramic lamination equipment according to claim 3 is characterized in that: The method for obtaining the optimal temperature curve comprises: Calculate the initial temperature based on the temperature influence data; Q temperature curves are preset, where Q is an integer greater than 1; According to the initial temperature, select from Q temperature curves temperature curves and construct a temperature curve set; According to the temperature impact data, the best temperature curve is selected from the temperature curve set; The calculation method of the initial temperature includes: Where, T c is the initial temperature, TC is the number of ceramic layers, SS1 is the first property coefficient, T h is the ambient temperature, RD i is the thermal conductivity of the i-th group of ceramic physical data, MD i is the density in the i-th group of ceramic physical data, ω1, ω2, ω3 are preset weight coefficients, i∈[1,m]; The method for constructing the temperature curve set includes: Obtain the starting temperature in Q temperature curves, where the starting temperature is the temperature value corresponding to the starting point in the temperature curve; sort the starting temperatures of the Q temperature curves from large to small to generate a sorting table, add the initial temperature to the sorting table, count the number of starting temperatures before the initial temperature in the sorting table, and mark it as a first number D, count the number of starting temperatures after the initial temperature, and mark it as a second number D′; like Then select the D starting temperatures before the initial temperature and the D starting temperatures after the initial temperature. The starting temperature; like Then select the D′ starting temperatures after the initial temperature and the D′ starting temperatures before the initial temperature. The starting temperature; like and Then filter out the The starting temperature, and the The starting temperature; A starting temperature set is constructed according to the screened starting temperatures; and a temperature curve set is constructed according to the temperature curves corresponding to the starting temperatures in the starting temperature set.

5. The temperature and pressure curve adaptive optimization control system of the multilayer ceramic lamination equipment according to claim 4 is characterized in that: The method for selecting the best temperature curve from the temperature curve set includes: Step a: Preset initialization temperature T max , minimum temperature T min , cooling coefficient δ and maximum number of iterations And let the current temperature T = T max ; Step b: randomly set a feasible solution χ, the feasible solution χ is the temperature curve, the temperature curve range is the temperature curve set, and the temperature curve range is the range of the feasible solution χ; Step c: determine the fitness function; The expression of fitness function is: f = ZL; In the formula, f is the fitness, ZL is the stacking quality; The lamination quality is the quality of the product obtained after laminating the ceramics according to the temperature curve under the condition of temperature influence data; Step d: Calculate the fitness f corresponding to the feasible solution χ; take the feasible solution χ as the current point, perform random perturbations in the neighborhood of the current point, obtain a new feasible solution χ′, and calculate the fitness f′ corresponding to the new feasible solution χ′; Step e: Calculate the fitness difference f″, the expression of the fitness difference f″ is f″=f′-f; If the fitness difference f″>0, let χ=χ′, that is, assign the value of the new feasible solution χ′ to the feasible solution χ; if the fitness difference f″≤0, calculate the probability p′, and let χ=χ′ according to the probability p′; the expression of probability p′ is: In the formula, e is a natural constant; Step f: Repeat steps d to e until the number of loops reaches the maximum number of iterations. When , the loop ends and enters step g; Step g: Set the current temperature T = T × δ, that is, cool down the current temperature in step a, and assign the value after cooling to the current temperature; set the maximum number of iterations The value of the maximum number of iterations after the reduction is assigned to the maximum number of iterations; Step h: Repeat steps d to g until the current temperature T < T min When , the cycle ends, and the temperature curve corresponding to the feasible solution χ is obtained and used as the optimal temperature curve.

6. The temperature and pressure curve adaptive optimization control system of the multilayer ceramic lamination equipment according to claim 5, characterized in that: The method for obtaining the stacking quality includes: The temperature curve and temperature influence data corresponding to the feasible solution χ are used as analysis data; the analysis data are input into the trained quality prediction model to predict the corresponding stacking quality; The training process of the quality prediction model includes: Pre-collect N groups of analysis data corresponding to the stacking qualities, and convert the analysis data and the corresponding stacking qualities into a corresponding set of feature vectors; Each group of feature vectors is used as the input of the quality prediction model. The quality prediction model takes a group of overlay qualities corresponding to each group of analysis data as output, and takes the actual overlay quality corresponding to each group of analysis data as the prediction target, and the actual overlay quality is the overlay quality corresponding to the analysis data collected in advance; minimizing the sum of prediction errors of all analysis data is used as the training target; the quality prediction model is trained until the sum of prediction errors converges and the training is stopped; the quality prediction model is a deep neural network model.

7. The temperature and pressure curve adaptive optimization control system of the multilayer ceramic lamination equipment according to claim 6 is characterized in that: The method for obtaining the optimal pressure curve includes: Calculate the initial pressure based on the pressure impact data; M pressure curves are preset, where M is an integer greater than 1; According to the initial pressure, select from M pressure curves pressure curves and construct a pressure curve set; the construction method of the pressure curve set is the same as the construction method of the temperature curve set; According to the pressure influence data, the best pressure curve is selected from the pressure curve set; the method of selecting the best pressure curve from the pressure curve set is consistent with the method of selecting the best temperature curve from the temperature curve set.

8. The temperature and pressure curve adaptive optimization control system of the multilayer ceramic lamination equipment according to claim 7, characterized in that: The calculation method of the initial pressure includes: P c =ψ1×TC+ψ2×SS2+ψ3×H; Where P c is the initial pressure, SS2 is the second property coefficient, H is the ambient humidity value, YD j is the hardness of the jth group of ceramic structure data, HD j is the thickness in the jth group of ceramic structure data, ψ1, ψ2, ψ3 are preset proportional coefficients, j∈[1,m′].

Images