A multi-parameter feedback-based silicon carbide polishing solution precision regulation system

Abstract

The application discloses a kind of based on multi-parameter feedback's silicon carbide polishing solution precision control system, specifically related to silicon carbide processing technical field, including silicon carbide polishing solution central control module, silicon carbide polishing solution parameter detection module, silicon carbide polishing solution primary control module, silicon carbide polishing solution secondary control module and silicon carbide polishing solution control optimization module;The silicon carbide polishing solution central control module is used to receive the acquisition data of parameter detection module, generates primary control instruction and secondary control instruction, simultaneously drives optimization module to carry out parameter optimization;The two-stage progressive control mechanism of the primary control and secondary control combination is used in the application, primary control is mainly adjusted to the basic characteristic parameter of polishing solution, to compensate basic characteristic deviation;Secondary control is adjusted to process adaptation parameter in combination with polishing effect feedback, to correct process adaptation deviation, improve the precision and efficiency of control.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of silicon carbide processing, in particular to a precision control system for silicon carbide polishing solution based on multi-parameter feedback. BACKGROUND

[0002] As a third-generation semiconductor material, silicon carbide (SiC) has excellent properties such as high thermal conductivity, high breakdown field strength, and high electron mobility, and is widely used in new energy vehicles, aerospace, 5G communication and other high-end fields. The polishing quality of silicon carbide substrate directly affects the preparation performance of subsequent devices, and the characteristic parameters of the polishing solution are the key factors that determine the polishing quality.

[0003] Traditional silicon carbide polishing solution control mainly adopts single parameter manual adjustment or static preset mode. For example, if the polishing efficiency is found to be low, the content of abrasive in the polishing solution is increased. Only the pH value of the polishing solution is concerned, and the pH value is changed by adding acid-base adjuster to adapt to the polishing demand of silicon carbide material, and it is believed that the appropriate pH value can ensure the stability of the polishing process. The formula of the polishing solution is set in advance according to experience, including the proportion of various components, and is not adjusted according to the actual processing condition, so as to realize the control of the silicon carbide polishing solution.

[0004] In actual application, the traditional silicon carbide polishing solution control still has the following defects: first, the control parameters are single, only a few indicators such as solid content or pH value are concerned, and the influence of key parameters such as particle size distribution and zeta potential on polishing effect is ignored; second, there is lack of real-time feedback mechanism, and the control response is lagging, so when the characteristics of the polishing solution change with the processing process, it cannot be compensated in time; third, the hierarchical control logic is not formed, the deviation of basic characteristics and the deviation of process adaptation interfere with each other, resulting in low parameter matching precision; fourth, the control parameters are mainly dependent on experience setting, and lack of scientific optimization means, so it is difficult to realize the optimization of polishing effect; therefore, it is of great significance to develop a precision control system based on multi-parameter feedback to improve the polishing quality of silicon carbide. SUMMARY

[0005] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present application provide a precision control system for silicon carbide polishing solution based on multi-parameter feedback to solve the problems raised in the background art.

[0006] To achieve the above-mentioned purpose, the present application provides the following technical scheme: a precision control system for silicon carbide polishing solution based on multi-parameter feedback, comprising:

[0007] The silicon carbide polishing solution central control module is used for receiving the collected data of the parameter detection module, generating primary control instructions and secondary control instructions, driving the optimization module to optimize parameters at the same time, and storing the data generated in the process of controlling the silicon carbide polishing solution, and constructing a silicon carbide polishing solution central control database.

[0008] The silicon carbide polishing liquid parameter detection module is used for collecting the basic characteristic parameters, process state parameters and polishing effect parameters of the polishing liquid in real time, constructing a silicon carbide polishing liquid detection data set, and transmitting the silicon carbide polishing liquid detection data set to the silicon carbide polishing liquid primary regulation and control module and the silicon carbide polishing liquid secondary regulation and control module.

[0009] The silicon carbide polishing liquid primary regulation and control module is used for judging the allowable interval range of the basic characteristic parameters of the polishing liquid in the silicon carbide polishing liquid detection data set, calculating the deviation of each parameter from a standard value according to a judgment abnormal result, performing regulation and control according to the deviation, evaluating the regulation and control result, and transmitting the regulation and control evaluation qualified result to the silicon carbide polishing liquid secondary regulation and control module.

[0010] The silicon carbide polishing liquid secondary regulation and control module is used for judging the allowable interval range of the polishing effect parameters in the silicon carbide polishing liquid detection data set based on the primary regulation and control evaluation qualified result, calculating the deviation of each parameter from a standard value according to a judgment abnormal result, performing regulation and control on the process state parameters according to the deviation, evaluating the regulation and control result, performing feedback according to the abnormal evaluation result, and obtaining a silicon carbide polishing liquid secondary regulation and control qualified result.

[0011] The silicon carbide polishing liquid regulation and control optimization module is used for generating a regulation and control parameter optimization scheme through an optimization algorithm based on the parameters generated in the silicon carbide polishing liquid regulation and control process, and feeding back the regulation and control parameter optimization scheme to the central control module.

[0012] Technical effects and advantages of the present application:

[0013] 1. The present application can collect and process the basic characteristic parameters, process state parameters and polishing effect parameters of the polishing liquid in real time, accurately understand the state and polishing effect of the polishing liquid, and thus realize more targeted and comprehensive regulation and control, timely adjust the polishing liquid parameters to adapt to different processing requirements, and improve the polishing quality and efficiency.

[0014] 2. The present application adopts a two-stage progressive regulation and control mechanism combining primary regulation and control and secondary regulation and control, the primary regulation and control mainly adjusts the basic characteristic parameters of the polishing liquid to compensate for the basic characteristic deviation, and the secondary regulation and control adjusts the process adaptation parameters in combination with the polishing effect feedback to correct the process adaptation deviation, thereby improving the regulation and control precision and efficiency.

[0015] 3. The present application uses a hybrid algorithm combining particle swarm optimization and BP neural network to iteratively optimize the regulation and control parameters based on historical regulation and control data and real-time feedback parameters through the optimization module, thereby not only improving the regulation and control precision and stability, but also reducing the need for manual intervention, reducing the operation difficulty and cost, and improving the flexibility and universality of the system. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1The overall flowchart of the present application.

[0017] Figure 2 The secondary control module of the silicon carbide polishing solution of the present application. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0019] Please refer to Figure 1 As shown in the figure, the present application provides a multi-parameter feedback-based precision control system for silicon carbide polishing solution, which comprises a silicon carbide polishing solution central control module, a silicon carbide polishing solution parameter detection module, a silicon carbide polishing solution primary control module, a silicon carbide polishing solution secondary control module, and a silicon carbide polishing solution control optimization module.

[0020] The silicon carbide polishing solution central control module is connected with all the other modules, the silicon carbide polishing solution parameter detection module is connected with the silicon carbide polishing solution primary control module, the silicon carbide polishing solution secondary control module is connected with the silicon carbide polishing solution primary control module and the silicon carbide polishing solution control optimization module respectively, and the silicon carbide polishing solution control optimization module is connected with the silicon carbide polishing solution central control module.

[0021] The silicon carbide polishing solution central control module is used for receiving the collected data of the parameter detection module, generating primary control instructions and secondary control instructions, driving the optimization module to perform parameter optimization, and storing the data generated in the silicon carbide polishing solution control process to build a silicon carbide polishing solution central control database;

[0022] It is particularly pointed out in this embodiment that the data generated in the silicon carbide polishing solution control process includes but is not limited to the collected raw data, processed data, control instructions, and historical control records.

[0023] The silicon carbide polishing solution parameter detection module is used for real-time collection of the basic characteristic parameters, process state parameters, and polishing effect parameters of the polishing solution, construction of a silicon carbide polishing solution detection data set, and transmission to the silicon carbide polishing solution primary control module and the silicon carbide polishing solution secondary control module, which includes:

[0024] A1: The basic characteristic parameters of the polishing solution include particle size distribution, solid content, pH value, viscosity, and zeta potential; the process state parameters of the polishing solution include flow rate, temperature, and jetting pressure; and the polishing effect parameters include polishing surface roughness, silicon carbide substrate material removal rate, and polishing surface shape error.

[0025] The embodiment needs to be specifically explained as follows: in order to ensure detection accuracy, the parameter detection module integrates a particle size analyzer, a solid content detector, a pH meter, a viscometer, a zeta potential instrument, a flow sensor, a temperature sensor, a pressure sensor, a rotation speed sensor, an optical profiler and a laser interferometer and the like. The laser interferometer can calibrate the detection result of the optical profiler in real time. The particle size analyzer is used to detect the particle size distribution of the abrasive in the polishing liquid. The solid content detector is used to detect the solid content of the polishing liquid. The pH meter is used to detect the pH value of the polishing liquid. The viscometer is used to detect the viscosity of the polishing liquid. The zeta potential instrument is used to detect the zeta potential of the polishing liquid. The flow sensor is used to detect the supply flow of the polishing liquid. The temperature sensor is used to detect the real-time temperature of the polishing liquid. The pressure sensor is used to detect the injection pressure of the polishing liquid. The optical profiler is used to detect the surface roughness and the face shape error of the silicon carbide substrate after polishing. The silicon carbide substrate material removal rate Rr is obtained by the difference between the thickness of the silicon carbide substrate before polishing and the thickness of the silicon carbide substrate after polishing, and the ratio of the polishing time point.

[0026] A2: the Min-Max normalization method is performed on the collected particle size distribution and the corresponding standard value, the solid content and the corresponding standard value, the pH value and the corresponding standard value, the viscosity and the corresponding standard value, the zeta potential and the corresponding standard value, the flow and the corresponding standard value, the temperature and the corresponding standard value, the injection pressure and the corresponding standard value, the circulation rate and the corresponding standard value, the surface roughness and the corresponding standard value, the removal rate and the corresponding standard value, and the face shape error and the corresponding standard value, respectively, to obtain the normalized parameter value X and the corresponding standard value X th of each parameter, wherein the threshold interval of each parameter in the Min-Max normalization method is (X min , i,max ), the lower limit value of the allowable interval of each parameter is (X std,min , std,max ) and belongs to (X min , max ), wherein the particle size distribution selects D50 (median particle size) as the core characteristic value, D50 is the particle size value whose cumulative proportion reaches 50% in the particle size distribution (for example, D50=2μm), and the normalized viscosity GH and the corresponding standard value GH th are obtained by taking the viscosity of the polishing liquid as an example. , The viscosity acquisition value is X, the standard value is X std , the viscosity threshold is (40, 60)mpa·s, the acquisition value is X=55mpa·s, the normalized GH is 0.75, the standard value is X std =50mpa·s, and the normalized GH th=0.5, deviation ΔGH=0.75-0.5=0.25, indicating a deviation of 25% from the standard value; finally, the normalized parameters are used to construct a silicon carbide polishing liquid detection data set;

[0027] It needs to be specifically explained in this embodiment that the standard value of each parameter is based on historical data, and the initial standard value is determined by orthogonal experiment, and then the polishing effect is optimized as the target, and the iteration is updated by the optimization module; the allowed range of each parameter is centered on the standard value, and the offset is set according to the parameter control accuracy and effect sensitivity, and the formula is: X std,min =X std -ΔX, X std,min =X std +ΔX, X std and ΔX are the standard value and the offset of the parameter respectively, the present application is precise control, the value of ΔX is 2% to 5% of the standard value; the threshold range of each parameter is the "safety red line" of the system, and the core depends on the hardware limit of the equipment, the material tolerance characteristics and the process failure critical point, once the calibration is completed, only when the equipment is replaced or the process is upgraded, the adjustment is made, wherein the basic characteristic parameters are calibrated according to the material chemical / physical tolerance limit, for example, zeta potential: test the critical potential of abrasive aggregation (-30mV when aggregation intensifies) and the critical potential of excessive dispersion (-50mV when abrasive settles), and calibrate [-50, -30]mV; wherein the process state parameters are calibrated according to the equipment hardware running limit, for example, flow: test the minimum stable output of the polishing liquid delivery pump (1.0L / min, lower than this value, the pump body idles) and the maximum safe output (3.0L / min, higher than this value, the motor is overloaded), and calibrate [1.0, 3.0]L / min; wherein the polishing effect parameters are calibrated according to the workpiece scrap / process failure critical value, for example, surface roughness: when R_a>2.0nm, the workpiece cannot meet the subsequent photolithography requirements, and when R_a<0.5nm, the polishing efficiency drops sharply, and the calibration is [0.5, 2.0]nm.

[0028] It needs to be specifically explained in this embodiment that the standard value anchors the optimal polishing effect; the allowed fluctuation interval provides process fault tolerance space; the threshold ensures the safety of equipment and process, and without the threshold, the parameters may be out of control to the extent of damaging the equipment or scrapping the workpiece.

[0029] The primary control module of the silicon carbide polishing liquid: the allowed interval range of the basic characteristic parameters of the polishing liquid in the silicon carbide polishing liquid detection data set is judged, the deviation of each parameter from the standard value is calculated according to the abnormal judgment result, the control is carried out according to the deviation, and the control evaluation is carried out, and the control evaluation qualified result is transmitted to the secondary control module of the silicon carbide polishing liquid, including:

[0030] B1: whether the original value corresponding to the i-th parameter of the basic characteristic of the polishing liquid in the silicon carbide polishing liquid detection data set belongs to the allowed interval (Xi,std,min , i,std,max ), if it belongs to the range, no adjustment is needed, otherwise, it indicates that the abnormality is determined, and the primary PID control is performed;

[0031] B2: first, based on the abnormality result, the deviation Δx i of the i-th parameter from the corresponding standard value is calculated i =x i -x i，std , x i and x i，std are the normalized collection value and the standard value of the i-th parameter, respectively, if only one parameter has a deviation, the primary PID control is directly performed on the parameter, if there are at least two parameters with deviations, the primary PID control is performed according to the size of the deviation Δx i for sorting (for example, the normalized deviation of the pH value +0.4 (40% of the range) is much larger than the solid content -0.15 (15% of the range), and the pH value needs to be controlled first); then the i-th parameter is subjected to the primary PID control of the corresponding component, and the adjustment amount U i (t) of the i-th parameter is obtained , t is the parameter sampling period, K i,p , K i,j and K i,d are the proportional coefficient, the integral coefficient and the differential coefficient of the i-th parameter, respectively;

[0032] It needs to be specifically explained in this embodiment that the proportional coefficient, the integral coefficient and the differential coefficient of each parameter can be determined in the order of first determining K i,p , then adjusting K i,j , and finally matching K i,d , for example, through the experimental control variable method, first, the proportional coefficient K p is calibrated, the integral coefficient K j =0 and the differential coefficient K d =0, a direct linear relationship between the parameter deviation and the corresponding adjustment amount is established, until the adjustment amount is found, and the ratio of the adjustment amount to the parameter deviation corresponding to the allowed range interval of the parameter value is the proportional coefficient K p (for example, the deviation is 0.02, and the adjustment amount is 0.1, so the proportional coefficient K i,p is 0.1 / 0.02=0.5), then based on the obtained proportional coefficient K p , the differential coefficient K d =0, the integral coefficient K j and the sampling period number m are set, the corresponding adjustment amount proportional coefficient K p and the integral coefficient K j are obtained, and the differential coefficient K d, the integral coefficient K of the parameter belonging to the allowed range interval after adjustment j , such as the basic characteristic parameters of particle size distribution, solid content, pH value, viscosity and zeta potential p / K j / K d may be 0.6 / 0.3 / 0.2, 0.8 / 0.4 / 0.1, 1.2 / 0.2 / 0.5, 0.7 / 0.3 / 0.3 and 1.0 / 0.1 / 0.4, respectively;

[0033] The primary control device of the embodiment includes an abrasive supply assembly, a pH adjusting assembly, a viscosity adjusting assembly and a dispersion stabilizing assembly. The abrasive supply assembly adjusts the particle size distribution and solid content of the polishing liquid. The pH adjusting assembly adds acid or alkali to the polishing liquid through a precision titration pump, and cooperates with a stirrer to ensure uniform mixing and achieve accurate pH adjustment. The viscosity adjusting assembly supplies solvent or thickening agent through a quantitative delivery pump according to the viscosity deviation to quickly correct the viscosity parameter. The dispersion stabilizing assembly uses an ultrasonic disperser to break the abrasive agglomeration, and combines a magnetic field stabilizer to maintain the abrasive dispersion state and adjust the zeta potential to the stable range.

[0034] B3: the adjustment amount U based on the i-th parameter i (t), the control result is evaluated, the relative deviation of the actual value after adjustment and the standard value is calculated first, and the deviation coefficient C of the i-th parameter is obtained i , , X i and X i,th are the actual collected value and the standard value of the i-th parameter, respectively, X i,max -X i,min is the difference between the upper and lower limit values of the i-th parameter, i.e. the threshold range; then the i-th parameter X k is detected for m times (for example, 3 times, with an interval of 1s each time), and the stability coefficient S of the i-th parameter is calculated i , ; then the comprehensive fitness FC of the primary PID control is calculated , i = 1 to 5 are particle size distribution, solid content, pH value, viscosity and zeta potential respectively; finally, if FC belongs to the excellent grade (for example, [0.9, 1.0]), it means that the regulation evaluation result is qualified, meeting the secondary regulation requirements of the polishing liquid, if FC belongs to the good grade (for example, [0.7, 0.9]), it means that the regulation evaluation result needs to be regulated by 1 / 3 of the adjustment amount of the parameter, if FC belongs to the general grade (for example, [0.5, 0.7]), it means that the regulation evaluation result is unqualified, indicating that there is an abnormal result of parameter deviation greater than the threshold range, repeating the regulation steps of the target deviation abnormal parameter, if FC belongs to the poor grade (for example, [0, 0.5]), it means that the regulation evaluation result is unqualified, stopping the primary PID regulation, and performing root cause analysis, including primary regulation equipment and basic characteristic parameter analysis;

[0035] Please refer to Figure 2 As shown in the figure, the secondary regulation module of the silicon carbide polishing liquid: based on the qualified result of the primary regulation evaluation, the allowed interval range of the polishing effect parameters is judged in the silicon carbide polishing liquid detection data set, the deviation of each parameter from the standard value is calculated according to the abnormal result, the process state parameters are regulated according to the deviation and the regulation result is evaluated, the feedback is carried out according to the abnormal evaluation result, and the qualified result of the secondary regulation of the silicon carbide polishing liquid is obtained, including:

[0036] C1: Based on the original value corresponding to all parameters of the polishing effect in the silicon carbide polishing liquid detection data set, it is judged whether it belongs to the allowed interval (X std,min , std,max ) of each parameter, if it belongs to, it is not necessary to adjust, otherwise, the deviation of the polishing effect parameters of removal rate and surface shape error from the corresponding standard value is calculated, and the polishing effect parameters are regulated according to the deviation size;

[0037] C2: When the removal rate is judged to be abnormal, the deviation ΔRr of the removal rate Rr from the corresponding standard value is calculated, ΔRr = Rr - Rr th , Rr and Rr th are the normalized collection value and the standard value of the removal rate respectively; then through the historical data, the flow-removal rate relationship model is calibrated: Q th = Q + K Q × | ΔRr | × sign (- ΔRr), K Q is the flow regulation coefficient, sign (- ΔRr) is the sign function, which ensures that the flow regulation direction matches the deviation direction, Q and Q threspectively; then the flow standard value output by the model is multiplied by the corresponding flow threshold range and then converted into a 4-20 mA current signal (for example, through inverse conversion of the normalized value to physical quantity (such as 0-1 corresponding to 0-10 L / min), the physical flow adjustment amount ΔQ = 0.25 x 10 = 2.5 L / min is obtained, 4 mA corresponds to 1 L / min, and 20 mA corresponds to 3 L / min), which is transmitted to the electric proportional valve; when ΔRr < 0, the current signal is increased, the valve opening is increased, and the flow is increased; when ΔRr > 0, the current signal is decreased, the valve opening is decreased, and the flow is decreased; finally, the removal rate after regulation is detected and evaluated; if the removal rate after regulation belongs to the corresponding allowable range, the regulation is stopped, indicating that the regulation is qualified, and the current flow is maintained; otherwise, the step is continued;

[0038] It needs to be specifically explained in this embodiment that the 4-20 mA current signal is an international standard signal in the field of industrial automation, which is formulated by the International Electrotechnical Commission (IEC) and is widely used in process control systems; based on the removal rate deviation (ΔRr), the size of the 4-20 mA current signal is changed to adjust the opening of the electric proportional valve, thereby controlling the polishing liquid flow, and finally the removal rate deviation is controlled within the allowable range.

[0039] C3: When the surface error in the polishing effect parameter is abnormal, the surface error (Wt at this time is the normalized surface error) of h x h points (for example, 200 x 200) is collected, the surface error Wt is multiplied by the corresponding threshold range to obtain the physical quantity Wt of the surface error, a surface error heat map is generated, and the substrate is divided into three regions according to the error value; the high error region is Wt > the upper limit value Wt std,max of the corresponding allowable range, the normal region is Wt std,min ≤ Wt ≤ Wt std,max , and the low error region is Wt ≤ Wt std,min ; then, for different regions of errors, the jet pressure compensation amount P 区 of the high error region and the low error region is calculated, P 区 = P 基 + Ky x (Wt 区 - Wt th ), P 基 is the reference pressure, corresponding to the jet pressure value Wt std,min of the normal region (for example, 0.3 MPa), Ky is the pressure compensation coefficient (calibrated by experiment, such as 0.2 MPa / μm), and Wt 区 is the average surface error of the region (for example, the average Wt = 0.7 μm in the high error region), and Wt th is the standard value of the surface error; then, based on the jet pressure compensation amount of the high error region, a pressure increasing instruction is sent to the corresponding pump group (for example, P gao= 0.3 + 0.2 x (0.7 - 0.4) = 0.36 MPa), a pressure compensation amount based on the low error area is sent to the corresponding pump group to send a pressure reduction command, and the pressure of the jet is raised and lowered by increasing / decreasing the motor frequency, based on the normal area, the current jet pressure and motor frequency are saved; finally, the face error distribution after regulation is detected and evaluated, that is, the area ratio of the high error area and the low error area is less than or equal to a threshold value (for example, less than or equal to 5%), and the average Wt of the polished full surface belongs to the allowed interval, the jet pressure regulation is stopped, indicating that the regulation is qualified, otherwise the step is repeated.

[0040] It needs to be specifically explained in this embodiment that the removal rate is strongly related to the flow rate and the face error is strongly related to the jet pressure by experimental calibration using the Pearson correlation coefficient.

[0041] C4: the temperature T in the process state parameter is compared with the standard value T th The temperature deviation AT is obtained by difference comparison, and the temperature adjustment amount U T (t) is obtained by a PID model. t is a parameter sampling period, K T,p , K T,j and K T,d are the proportional coefficient (for example, 2.0), the integral coefficient (for example, 0.5) and the differential coefficient (for example, 1.0) of the temperature adjustment amount respectively; when the original value corresponding to the temperature T is greater than the upper limit value of the corresponding allowed interval, U T (t) outputs a negative value to trigger the opening of the cooling coil solenoid valve, and when the original value corresponding to the temperature T is less than the lower limit value of the corresponding allowed interval, U T (t) outputs a positive value to trigger the heating jacket to be powered on, and when the temperature T belongs to the allowed interval, the heating jacket and the cooling coil are in standby state to maintain the temperature stability; at the same time, the speed sensor signal of the polishing liquid circulating pump is received to detect the speed and the corresponding polishing liquid temperature in real time, and when the absolute difference between the polishing liquid temperature and the upper limit value of the allowed interval is less than a corresponding threshold value (for example, 0.5℃), it is indicated that the speed causes the polishing liquid temperature to develop in the direction deviating from the allowed interval, triggering the pre-opening of the cooling coil feedforward compensation mechanism; finally, the polishing liquid temperature is detected and evaluated, and if the regulated polishing liquid temperature belongs to the corresponding allowed interval, the regulation is stopped to maintain the current temperature, indicating that the regulation is qualified, otherwise the step is continued.

[0042] It needs to be specifically explained in this embodiment that the speed of the polishing liquid circulating pump will generate frictional heat, thereby disturbing the polishing liquid temperature; when the environmental temperature changes (such as from 25℃ to 30℃), the heat dissipation efficiency will decrease, causing the potential risk of the polishing liquid temperature breaking through the optimal interval (such as 26℃).

[0043] C5: Based on the polishing surface roughness in the polishing effect parameter, it is judged whether the collected original value belongs to the allowed interval. If it belongs to the allowed interval, it indicates that the secondary regulation and control of the silicon carbide polishing liquid is good, otherwise, the steps C1-C4 are repeated;

[0044] It is specifically pointed out in this embodiment that the process parameters of flow rate, temperature and jetting pressure all have different influences on the surface roughness, so the polishing surface roughness is taken as a comprehensive factor for evaluating the secondary regulation and control effect of the polishing liquid.

[0045] The silicon carbide polishing liquid regulation and control optimization module: based on the parameters generated in the silicon carbide polishing liquid regulation and control process, an optimization scheme of the regulation and control parameters is generated through an optimization algorithm and fed back to the central control module, including:

[0046] D1: The basic characteristic parameters and process state parameters in the historical regulation and control data are taken as input samples, and the corresponding polishing effect parameters are taken as output samples. The BP neural network model is trained through the mean square error loss function L. When L is less than the corresponding threshold value (for example, L<10 --4 ), it indicates that the BP neural network model is trained, , 3 is the polishing effect of 3 parameters, y J and y J,m are the actual value and the model output value of the Jth parameter, respectively;

[0047] D2: Taking the optimal polishing effect parameter as the target, the fitness function fit is minimized, , R a , Wt, R r and R r,th are the normalized polishing surface roughness, surface shape error, removal rate and corresponding standard value, respectively, and a1, a2 and a3 represent the corresponding weights, for example, a1=0.4, a2=0.3 and a3=0.3; then set the particle swarm optimization algorithm to randomly generate D particles (for example, 50 particles), each particle represents a combination of input samples. For each particle, input its parameters into the trained BP neural network to obtain the predicted polishing effect parameters, and substitute them into the fitness function to calculate fit. Then, the particle velocity update function and the particle position update function are used for iteration. After each iteration, the individual optimal pbest and the global optimal gbest of the input samples are updated. Finally, when the global optimal gbest corresponding to the fitness function value fit changes by less than the corresponding threshold value (for example, from fit0.3256 to 0.3255, the change is 0.0001) for n1 consecutive iterations (for example, 10 times), the iteration is stopped. At this time, the global optimal gbest is the optimal combination of the basic characteristic parameters and the process state parameters, and each parameter in the optimal combination is de-normalized to restore the actual physical quantity to obtain the optimization scheme of the regulation and control parameters, which is fed back to the central control module.

[0048] Secondly: the drawings of the disclosed embodiments only involve the structures involved in the disclosed embodiments, other structures can refer to the general design, and in the case of no conflict, the same embodiments and different embodiments of the present application can be combined with each other;

[0049] Finally: the above only describes the preferred embodiments of the present application and is not used to limit the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A multi-parameter feedback based precision control system for silicon carbide polishing solution, characterized in that: The application relates to a carbonized silicon polishing liquid central control module, a carbonized silicon polishing liquid parameter detection module, a carbonized silicon polishing liquid primary regulation module, a carbonized silicon polishing liquid secondary regulation module and a carbonized silicon polishing liquid regulation optimization module. The carbonized silicon polishing liquid central control module is used for receiving collected data of the parameter detection module, generating primary regulation instructions and secondary regulation instructions, simultaneously driving the optimization module to perform parameter optimization, and storing data generated in the carbonized silicon polishing liquid regulation process and constructing a carbonized silicon polishing liquid central control database. The carbonized silicon polishing liquid parameter detection module is used for collecting basic characteristic parameters, process state parameters and polishing effect parameters of the polishing liquid in real time, constructing a carbonized silicon polishing liquid detection data set, and transmitting the carbonized silicon polishing liquid detection data set to the carbonized silicon polishing liquid primary regulation module and the carbonized silicon polishing liquid secondary regulation module. The carbonized silicon polishing liquid primary regulation module is used for judging the basic characteristic parameters of the polishing liquid in the carbonized silicon polishing liquid detection data set, calculating the deviation of each parameter from a standard value according to an abnormal judgment result, regulating according to the deviation, evaluating the regulation result, and transmitting the regulation evaluation qualified result to the carbonized silicon polishing liquid secondary regulation module. The silicon carbide polishing liquid primary regulation module is regulated according to the deviation: first, based on the judgment of abnormal results, the deviation Δx of the i-th parameter and the corresponding standard value is calculated i , Δx i = x i - x i，std , x i and x i，std are the normalized acquisition value and the standard value of the i-th parameter, respectively, if only one parameter has a deviation, the secondary parameter is directly regulated by the primary PID, if at least two parameters have a deviation, the primary PID is regulated according to the size of the deviation Δx i Sort and regulate; then the i-th parameter is regulated by the corresponding component of the primary PID, and the i-th parameter is regulated U i (t), , t is the parameter sampling period, K i,p , K i,j and K i,d and respectively, the proportional coefficient, integral coefficient and differential coefficient of the i-th parameter; The carbonized silicon polishing liquid secondary regulation module is used for judging the polishing effect parameters in the carbonized silicon polishing liquid detection data set based on the primary regulation evaluation qualified result, calculating the deviation of each parameter from a standard value according to an abnormal judgment result, regulating the process state parameters according to the deviation, evaluating the regulation result, feeding back the abnormal evaluation result, and obtaining the carbonized silicon polishing liquid secondary regulation qualified result. The carbonized silicon polishing liquid regulation optimization module is used for generating a regulation parameter optimization scheme through an optimization algorithm based on the parameters generated in the carbonized silicon polishing liquid regulation process and feeding back the regulation parameter optimization scheme to the central control module. 2.The multi-parameter feedback based silicon carbide polishing solution precision control system of claim 1, wherein: The allowed interval range judgment in the primary regulation module of the silicon carbide polishing liquid is that whether the original value corresponding to the i th parameter of the polishing liquid basic characteristics in the silicon carbide polishing liquid detection data set belongs to the allowed interval of the i th parameter (X i,std,min ,X i,std,max ) is judged, if it belongs to, no adjustment is needed, otherwise, the primary PID regulation is performed. 3.The multi-parameter feedback based silicon carbide polishing solution precision control system of claim 1, wherein: The evaluation of the regulation result in the primary regulation module of the silicon carbide polishing solution is based on the adjustment amount U of the i-th parameter i (t), the evaluation of the regulation result is to calculate the relative deviation of the actual value after regulation and the standard value, and obtain the deviation coefficient C of the i-th parameter i , , X i and X i,th are the actual collection value and the standard value of the i-th parameter respectively, X i,max -X i,min is the difference between the upper and lower limit values of the i-th parameter, that is, the threshold range Then the i-th parameter X is detected continuously m times i,k , the stability coefficient S of the i-th parameter is calculated i , ; then the comprehensive fitness FC of the primary PID control is calculated, , i=1 to 5 are particle size distribution, solid content, pH value, viscosity and zeta potential respectively; finally, if FC belongs to the excellent grade, it means that the control evaluation result is qualified and meets the secondary control requirements of the polishing liquid, if FC belongs to the good grade, it means that the control evaluation result needs to be adjusted by 1 / 3 of the adjustment amount, if FC belongs to the general grade, it means that the control evaluation result is unqualified, which means that there is an abnormal result with a parameter deviation greater than the threshold range, and the target abnormal parameter is repeatedly controlled, if FC belongs to the poor grade, it means that the control evaluation result is unqualified, and the primary PID control is stopped, and the root cause is investigated, including primary control equipment investigation and basic characteristic parameter investigation.

4. The multi-parameter feedback based precision control system for silicon carbide polishing solution of claim 1, wherein: The range of the allowed interval in the secondary control module of the silicon carbide polishing liquid is judged based on the original value of all parameters corresponding to the polishing effect in the silicon carbide polishing liquid detection data set, whether it belongs to the allowed interval of each parameter (X std,min ,X std,max ), if it belongs to the allowed interval, no adjustment is needed, otherwise, the deviation of the removal rate and the surface shape error parameters in the polishing effect from the corresponding standard value is calculated, and the polishing effect parameters are prioritized according to the deviation size.

5. The multi-parameter feedback based precision control system for silicon carbide polishing solution of claim 1, wherein: The secondary regulation module of the silicon carbide polishing solution comprises: when the removal rate is judged to be abnormal, calculating the deviation ΔRr of the removal rate Rr and the corresponding standard value, ΔRr=Rr-Rr th , Rr and Rr th are the normalized collection values and standard values of the removal rate, respectively; then through historical data, an experimental calibration flow-removal rate relationship model is determined: Q th =Q+K Q ×|ΔRr|×sign(-ΔRr), K Q is a flow regulation coefficient, sign(-ΔRr) is a sign function, Q and Q th are the normalized collection values and standard values of the flow, respectively; then the flow standard value output by the model is multiplied by the corresponding flow threshold range and then converted into a 4-20mA current signal, which is transmitted to an electric proportional valve; when ΔRr<0, the current signal is increased, the valve opening is increased, and the flow is increased; when ΔRr>0, the current signal is decreased, the valve opening is decreased, and the flow is decreased; finally, the regulated removal rate is detected and evaluated; if the regulated removal rate belongs to the corresponding allowable range, the regulation is stopped, which indicates that the regulation is qualified, the current flow is maintained, otherwise, the step is continued. 6.The multi-parameter feedback based silicon carbide polishing solution precision control system of claim 1, wherein: The secondary regulation module of the silicon carbide polishing liquid further comprises: when the surface error in the polishing effect parameter is abnormal, collecting the surface error of h x h points, multiplying the surface error Wt by the corresponding threshold range to obtain the physical quantity Wt of the surface error, generating a surface error thermodynamic map, and dividing the substrate into three regions according to the error value, wherein the high error region is Wt> the upper limit value Wt of the corresponding allowable interval std,max , the normal region is Wt std,min ≤Wt≤Wt std,max , and the low error region is Wt≤Wt std,min ; then, according to the error of different regions, calculating the jet pressure compensation amount P 区 of the high error region and the low error region, P 区 =P 基 +Ky×(Wt 区 -Wt th ), P 基 is the reference pressure, the jet pressure value corresponding to the normal region, Ky is the pressure compensation coefficient, Wt 区 is the average surface error of the region, and Wt th is the standard value of the surface error; then, sending a pressure increase instruction to the corresponding pump group based on the jet pressure compensation amount of the high error region, sending a pressure decrease instruction to the corresponding pump group based on the jet pressure compensation amount of the low error region, and saving the current jet pressure and motor frequency based on the normal region; finally, detecting the distribution of the regulated surface error and evaluating, that is, when the area ratio of the high error region and the low error region is less than or equal to a threshold value, and the average Wt of the polishing full surface belongs to the allowable interval, stopping the jet pressure regulation, which indicates that the regulation is qualified, otherwise, repeating the step.

7. The multi-parameter feedback based precision control system for silicon carbide polishing solution of claim 1, wherein: The secondary regulation module of the silicon carbide polishing solution further comprises: regulating the temperature T in the process state parameters to a standard value T th The difference is compared to obtain the temperature deviation ΔT, and the temperature adjustment amount U is obtained by the PID model T (t); when the original value corresponding to the temperature T is greater than the upper limit value of the corresponding allowable interval, U T (t) outputs a negative value to trigger the opening of the cooling coil solenoid valve, and when the original value corresponding to the temperature T is less than the lower limit value of the corresponding allowable interval, U T (t) outputs a positive value to trigger the heating jacket to be powered on, and when the temperature T belongs to the allowable interval, the heating jacket and the cooling coil are in a standby state to maintain the temperature stable; at the same time, the speed sensor signal of the polishing solution circulating pump is received to detect the speed and the corresponding polishing solution temperature in real time, and when the absolute difference between the polishing solution temperature and the upper limit value of the allowable interval is less than the corresponding threshold value, it is indicated that the speed causes the polishing solution temperature to develop in the direction deviating from the allowable interval, and a feedforward compensation mechanism of the cooling coil is triggered to be opened in advance; finally, the polishing solution temperature is detected and evaluated, and if the regulated polishing solution temperature belongs to the corresponding allowable interval range, the regulation is stopped to maintain the current temperature, which indicates that the regulation is qualified, otherwise the step is continued.

Images