Method and system for constructing chemical plating solution preparation model based on RNAS

Abstract

The present invention relates to a method and system for constructing an RNAS-based electroless plating solution preparation model, belonging to the technical field of the integration of artificial intelligence control and electroless plating reduction. The method comprises: obtaining formula data for the electroless plating solution to be prepared; obtaining a dimensional data set of the coating area of ​​the workpiece to be processed and electrode potential data indicating the redox strength of the metal to be electrolessly plated, and calculating the modeled film thickness of the workpiece; performing an actual electroless plating operation and measuring the actual film thickness of the workpiece; using the modeled film thickness and the actual film thickness of the workpiece that satisfy a preset relationship for training an RNAS model system to classify the electroless plating solution formula data; the present invention classifies the electroless plating solution formula data into "usable formula" or "unusable formula" by constructing an RNAS model, and uses this standard to strictly manage the amount of reducing agent used in the preparation of the electroless plating solution, thereby achieving the effect of accurately and rapidly screening the electroless plating solution formula data.

Description

Technical Field

[0001] The present invention relates to a method and system for constructing an RNAS-based chemical plating solution preparation model, and belongs to the technical field of integration of artificial intelligence control and chemical plating reduction. Background Art

[0002] The metal plating deposition of semiconductor electronic components is a unique characterization technology that is sensitive to the local electrochemical-physical environmental structure of metal ions during the electroless plating process. It has a wide range of applications in the fields of physical, electrochemical, and high-end chemical plating manufacturing. During the production and operation of plating production equipment, the metal ions and reducing agent components in the electroless plating solution, under the electrochemical-physical environmental conditions, have numerous and complex influences on the metal plating deposition. Therefore, due to the interference of various influencing factors, the actual deposited metal coating will have various differences. In mild cases, the additive or reducing agent component is too high, making the coating area difficult to control and the coating precipitation too fast and rough. In severe cases, the additive or reducing agent component is too low, resulting in a lack of coating density or even the inability to precipitate the desired metal coating.

[0003] At present, the preparation method of chemical plating solution adopts the usual golden section method. Its research and development requires a large amount of solution preparation work. At the same time, it is necessary to have chemical plating equipment modules for processing and evaluating plated samples. The R&D cycle is long, and it is difficult to adapt to the current semiconductor electronic components and the rapid development of various precision chemical plating solutions. Therefore, exploring and creating a systematic method for quickly preparing chemical plating solutions with short cycles and precision has become a very important topic. Summary of the Invention

[0004] In order to improve the preparation accuracy of chemical plating solutions and shorten the R&D cycle, the present invention provides a method and system for constructing a chemical plating solution preparation model based on RNAS. The technical solution is as follows:

[0005] A first object of the present invention is to provide a method for constructing a chemical plating solution configuration model, the method comprising:

[0006] Step 1: Obtain the formula data of the chemical plating solution to be prepared and construct an initial formula data set;

[0007] Step 2: Obtain the dimension data set of the plated area to be processed and the electrode potential data of the redox strength of the metal to be chemically plated. Calculate the mass of the chemically plated metal according to the general formula of the redox reaction, and calculate the film thickness of the plated model based on the dimension data. h 建模厚度 ;

[0008] Step 3: Randomly extract chemical plating solution formula data from the initial formula data set, use the chemical plating equipment module to perform actual chemical plating operation on the plated workpiece, and measure the actual film thickness of the plated workpieceh 实测厚度 ;

[0009] Step 4: Model the film thickness of the plated part h 建模厚度 and the measured film thickness of the plated parts h 实测厚度 Compare them, when the two satisfy the following relationship:

[0010] h 实测厚度 (100%-5%)≤ h 建模厚度 ≤ h 实测厚度 (100%+5%)

[0011] Then save the plating thickness of the plated part model h 建模厚度 The corresponding chemical plating solution formula data is used for training the RNAS model system;

[0012] If the above relationship is not satisfied, the chemical plating solution formula data is corrected, and the actual chemical plating operation is performed again using step 3 and the actual film thickness of the plated part is measured. h 实测厚度 ; Until the above relationship is satisfied, the chemical plating solution formula data is saved for RNAS model training;

[0013] Step 5: Model the film thickness of the plated part h 建模厚度 and the measured film thickness of the plated parts h 实测厚度 As input, the RNAS model is trained to classify the chemical plating solution formula data, and a classification model for the chemical plating solution formula data is established.

[0014] Optionally, the parts to be plated include: precision terminals, lead frames, wafer chips and precision decorations.

[0015] Optional metal coatings include:

[0016] Single metal coatings, including Au, Ag, Ni, Sn, Cu, Pd, Rh, Pt;

[0017] Alloy coatings include Au-Ni, Pd-Ni, Ni-P, W-Ni, Ag-Sn, Au-Sn, Rh-Ru and Pt-Rh or Au-W-Ni ternary or higher alloy metals.

[0018] Optionally, the chemical plating solution formula data includes:

[0019] Metal salt, which can be a single coating or an alloy coating;

[0020] Complexing agents, including malonic acid, succinic acid, and cyclohexanedicarboxylic acid;

[0021] Stabilizers, including citric acid, tartaric acid, and ethylenediaminetetraacetic acid;

[0022] electrolytes, including sodium edetate, ammonium formate, and ammonium acetate;

[0023] pH adjusters, including sulfuric acid, aminosulfonic acid, and methanesulfonic acid;

[0024] Reducing agents include sodium borohydride, sodium sulfite, and thiourea dioxide.

[0025] Optionally, the computing system for training the RNAS model includes modeling of sensitive condition parameters, and the sensitive condition parameters include: type of chemical plating solution, redox potential of metal ions, redox potential of reducing agent, specific gravity of chemical plating solution, solution temperature, chemical plating time, surface area of ​​plating area, metal density of coating layer and flow rate of chemical plating solution.

[0026] Optionally, it also includes constructing a set of parameters for the feeling of sudden change, wherein the parameters for the feeling of sudden change include: the tank body, the pump for conveying the chemical plating solution, the length and diameter of the pipeline for conveying the chemical plating solution, the semiconductor electronic plated parts to be processed, and the mold for chemical plating.

[0027] A second object of the present invention is to provide a system for constructing a chemical plating solution configuration model, for implementing the method for constructing a chemical plating solution configuration model as described in any one of the above items, the system comprising:

[0028] Memory 310, for storing recipe data and thickness data;

[0029] The data set processing system 200 is used to process the matching relationship between recipe data and thickness data, and includes: an electroless plating reduction plating operation module 210, an electroless plating equipment module 220, an electroless plating film thickness calculation module 230, and a plating film thickness threshold determination module 240; the electroless plating reduction plating operation module 210 is used to obtain recipe parameters and calculate the relationship between the electrode potentials of the metal ions and the reducing agent in the electroless plating solution; the electroless plating equipment module 220 is used to perform the actual electroless plating operation; the electroless plating film thickness calculation module 230 is used to calculate the modeled thickness; and the plating film thickness threshold determination module 240 is used to determine whether the modeled thickness matches the measured thickness.

[0030] RNAS model training system 100 is used to train and classify chemical plating solution formulas.

[0031] Optionally, the RNAS model training system 100 includes:

[0032] Training module 110, used for comparison training between modeled film thickness of plated parts and measured film thickness of plated parts;

[0033] a stability generation module 120 for processing the ordered arrangement and trend of the measured coating thickness;

[0034] The chemical plating reduction component ratio calculation module 130 is used for simulating the chemical plating solution formula ratio corresponding to the measured coating thickness;

[0035] The model morphology discrimination module 140 is used to discriminate the RNAS modeling morphology based on the calculation result of the simulated chemical plating solution formula ratio.

[0036] The third object of the present invention is to provide a method for preparing a chemical plating solution based on an RNAS model, wherein the model constructed by any of the above methods is used to determine the formula, comprising:

[0037] Accurately weigh each component;

[0038] Keep the concentration of the basic component constant and use the reducing agent as a variable parameter;

[0039] Calculate the modeled thickness and compare it with the measured thickness;

[0040] The RNAS model is used to classify and identify recipes that meet the threshold conditions.

[0041] Optionally, the RNAS model identification result includes:

[0042] Available recipes: Modeling thickness data meets the morphology threshold range;

[0043] Unusable recipe: The modeling thickness data does not meet the topography threshold range.

[0044] Optionally, an X-ray film thickness analyzer is used to measure the film thickness.

[0045] The beneficial effects of the present invention are:

[0046] The present invention improves and constructs an RNAS network operation model through an electrochemical reaction model for training. The constructed RNAS network outputs a modeled coating thickness data processing result obtained by calculating the chemical plating solution formula that meets the threshold range as an "usable formula"; while the modeled coating thickness data processing result obtained by calculating the chemical plating solution formula that exceeds the threshold range is an "unusable formula". This standard is used to strictly control the high-end quality requirements of the chemical plating solution preparation.

[0047] In addition, a threshold discrimination module for the coating thickness of plated parts is used to simulate and monitor the appearance, shape, color and overall morphological characteristics of semiconductor devices after chemical plating. Furthermore, by meeting the standards of a minimum threshold of -5% of the coating specification value and a maximum threshold of +5% of the coating specification value, the accuracy of RNAS network training is improved, and the training distribution of the chemical plating solution formula associated with the coating thickness is quickly realized, thereby obtaining the optimal standard of the RNAS operation mechanism model, achieving accurate and rapid identification of the screening results of available or unavailable formulas, and obtaining the preparation method of the chemical plating solution.

[0048] Based on the screening results of the present invention, the available formula conditions of chemical plating solutions of various different monomeric metal salts, divalent metal salts and ternary or higher metal salts can be quickly established in the actual production process, and then the optimal chemical plating control method of semiconductor electronic components can be obtained through the chemical plating equipment module. This can not only quickly achieve the accuracy of predicting the local coating film thickness of semiconductor electronic components and greatly reduce the error with the actual coating film thickness of chemically plated products, but also further improve the chemical plating device technology, promote the improvement of the uniformity of the coating film thickness of semiconductor electronic components, and meet the high quality requirements of high-end semiconductor electronic component products. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 It is a simplified structural diagram of the RNAS-based chemical plating solution preparation model of the present invention.

[0051] Figure 2 The present invention is a flowchart of a method and system for constructing a chemical plating solution preparation model based on RNAS.

[0052] Figure 3 It is a schematic diagram of a semiconductor electronic component test piece to be processed in the third embodiment of the present invention.

[0053] Figure 4 Schematic diagram of the nickel-plated area of ​​each unit in the semiconductor electronic component experimental piece to be processed in Example 3 of the present invention.

[0054] Figure 5 Schematic diagram of the platinum-plated area of ​​each unit in the semiconductor electronic component experimental piece to be processed in Example 3 of the present invention.

[0055] Figure 6Schematic diagram showing the variation trend of the thickness of the electroless plating platinum with the reducing agent concentration in the RNAS model in Example 3 of the present invention.

[0056] 100- RNAS model training system; 110- training module; 120- stability generation module; 130- chemical plating reduction component ratio calculation module; 140- model morphology discrimination module;

[0057] 200-dataset processing system; 210-chemical plating reduction plating operation module; 220-chemical plating equipment module; 230-chemical plating film thickness calculation module; 240-plating film thickness threshold judgment module;

[0058] 300-RANS simulation model; 310-memory;

[0059] 10-copper plating area; 20-silver plating area; 21-center of chemical plating area. DETAILED DESCRIPTION

[0060] To make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0061] Example 1:

[0062] This embodiment provides a method for constructing a chemical plating solution configuration model. The model is based on the Reynolds Averaged Navier-Stokes (RANS) Turbulence Models. The RANS model construction process mainly includes two parts: the construction of a chemical redox plating data processing system and the construction of a RANS Reynolds Averaged Navier-Stokes (RANS) turbulence model training system.

[0063] First, the chemical redox plating data processing system is constructed based on the chemical plating solution formula, the chemical plating equipment module, and the semiconductor electronic components to be processed. The data of each component in the chemical plating solution formula, the feeling data and dimensions of various components in the chemical plating equipment module, the dimensions of the semiconductor electronic components, the coating area, and other data are collected. The specific steps include:

[0064] Step 1: Obtain data on the components of the chemical plating solution to be prepared, the feel data and dimensions of various components in the chemical plating equipment module, the dimensional data of the processed semiconductor electronic components, and the coating thickness and area.

[0065] The chemical plating solution to be prepared includes the following components in concentration:

[0066] Table 1 Component data of the chemical plating solution to be prepared

[0067]

[0068] The stiffness data and dimensions of various components in the chemical plating equipment module do not change during the chemical plating process and are not listed in detail.

[0069] Step 2: Obtain the quantity of each component of the chemical plating solution to be prepared, wherein the quantities of 1 to 5 remain unchanged, and only the sixth reducing agent, sodium borohydride, is used as a variable parameter.

[0070] Step 3: Calculate the thickness of the modeled coating based on the quantity parameters of the platinum electroless plating solution prepared in step 1. h 建模厚度 The calculation method is based on the metal platinum electrode potential E (Pt n+ / Pt), the unit is V (volt).

[0071] Its general formula is:

[0072] Pt(IV) → (II)[PtCl6] 2- +2e - =[PtCl4] 2- +2Cl - E = 0.68 V

[0073] Pt(II) → (0)[PtCl4] 2- + 2e - = Pt + 4Cl - E = 0.755 V

[0074] The electrode potential E(B n+ / B), the unit is V (volt).

[0075] B(IV) → (III)[BH ４ ] - —e - →B(OH)3+2H2E = -1.3 V

[0076] The general formula of the chemical reduction reaction is:

[0077] Na2(PtCl6) + Na(BH4) + 6H2O→Pt + B(OH)3+ 6HCl

[0078] In the formula, sodium hexachloroplatinate and sodium borohydride are based on the redox reaction, and the metal ions in the solution are reduced by sodium borohydride reducing agent and plated and deposited on the surface of semiconductor electronic components to obtain the modeled coating thickness h 建模厚度 .

[0079] Step 4: Randomly extract the standard conditions for coating thickness calculated based on the chemical plating solution formula, use the prepared platinum chemical plating solution, and perform actual chemical plating operation on the semiconductor plated part to be processed through the chemical plating module. After the chemical plating is completed, use an X-ray film thickness analyzer to measure the actual film thickness data of the plated part. h 实测厚度 .

[0080] Step 5: Model the film thickness of the plated part h 建模厚度 and the measured film thickness of the plated parts h 实测厚度 Compare them, when the two satisfy the following relationship:

[0081] h 实测厚度 (100%-5%)≤ h 建模厚度 ≤ h 实测厚度 (100%+5%)

[0082] Then save the plating thickness of the plated part model h 建模厚度 The corresponding chemical plating solution formula data is used for training the RNAS model system.

[0083] If the above relationship is not satisfied, the formula data of the standard chemical plating solution is adjusted according to the actual film thickness of the plated part. h 实测厚度 Make corrections and calculate the corrected chemical plating solution formula data standard conditions, return to step 3 to recalculate the simulation modeling plating film thickness h 建模厚度 , and re-based on the chemical plating conditions for modeling, obtain new measured coating thickness data through the chemical plating equipment module h 实测厚度 , and further determine the thickness of the modified plated modeling film h 建模厚度 Whether the threshold range is met until the modeling coating thickness is h 建模厚度 Only when the above relationship is met can the data set be used for the RNAS training system.

[0084] Step 6: Calculate the modeled coating thickness based on the chemical plating solution formula h 建模厚度 and the measured film thickness of the plated parts h 实测厚度 Import the trained RNAS operation system, and the results of the RNAS operation system comparison processing are divided into two categories:

[0085] Available formula: The modeled coating thickness data processing results obtained by calculating the chemical plating solution formula meet the morphology threshold range;

[0086] Unusable formula: The modeled coating thickness data processing results obtained by calculating the chemical plating solution formula do not meet the morphology threshold range.

[0087] The Navier-Stokes equations of the RNAS model are mathematical equations that describe turbulent flow. They are obtained by averaging the fluid flow and can describe the motion patterns of turbulent flow. The equations are as follows:

[0088]

[0089] in, This term describes the change of flow rate over time and is 0 in steady-state calculations (steady-state calculations); The term representing the flow effects carried by the flow itself; It is the expression item of the influence of pressure difference on flow; This term represents the effect (diffusion) of smoothing the flow distribution due to fluid viscosity and has the function of stabilizing numerical analysis calculations; This is a term describing external forces. If there is no external force, it is 0.

[0090] By using the Navier-Stokes turbulence calculation equation of the RNAS model, the flow conditions in the chemical plating equipment module are simulated for the prepared chemical plating platinum solution to obtain accurate turbulence simulation results. Combined with the electrode potential of the metal used in the chemical plating solution, the thickness data of the modeled chemically plated metal layer is accurately calculated and obtained under different concentrations of reducing agents. h 建模厚度 The processing result.

[0091] Example 2:

[0092] This embodiment provides a system for constructing a chemical plating solution configuration model, which is used to implement the method for constructing a chemical plating solution configuration model described in Example 1. The system of this embodiment includes:

[0093] Memory 310, for storing recipe data and thickness data;

[0094] The data set processing system 200 is used to process the matching relationship between recipe data and thickness data, and includes: an electroless plating reduction plating operation module 210, an electroless plating equipment module 220, an electroless plating film thickness calculation module 230, and a plating film thickness threshold determination module 240; the electroless plating reduction plating operation module 210 is used to obtain recipe parameters and calculate the relationship between the electrode potentials of the metal ions and the reducing agent in the electroless plating solution; the electroless plating equipment module 220 is used to perform the actual electroless plating operation; the electroless plating film thickness calculation module 230 is used to calculate the modeled thickness; and the plating film thickness threshold determination module 240 is used to determine whether the modeled thickness matches the measured thickness.

[0095] RNAS model training system 100 is used to train and classify chemical plating solution formulas.

[0096] The RNAS model training system 100 includes:

[0097] Training module 110, used for comparison training between modeled film thickness of plated parts and measured film thickness of plated parts;

[0098] a stability generation module 120 for processing the ordered arrangement and trend of the measured coating thickness;

[0099] The chemical plating reduction component ratio calculation module 130 is used for simulating the chemical plating solution formula ratio corresponding to the measured coating thickness;

[0100] The model morphology discrimination module 140 is used to discriminate the RNAS modeling morphology based on the calculation result of the simulated chemical plating solution formula ratio.

[0101] Example 3:

[0102] This embodiment introduces the technical effects of the present invention in combination with the actual chemical plating solution configuration process.

[0103] The semiconductor electronic component test piece to be processed in this embodiment is as follows Figure 3 As shown in the figure, the copper alloy material is 60×60mm and the thickness is 0.127mm; there are 16 basic units in total. The copper plating area of ​​each unit is as follows Figure 4 The size of 10 is 11.5mm×11.5mm, and its area is 132.25mm 2 ; The total area of ​​nickel-plated double sides of a semiconductor electronic component is 16×132.25×2=4232mm 2 ; In addition, the silver-plated area of ​​each unit is as follows Figure 5 The size of 20 is 7.3mm×7.3mm, and its area is 53.29mm 2 The total platinum-plated double-sided area of ​​a semiconductor electronic component is 2×16×53.29=1705.28mm2 .

[0104] The center position of the plating thickness detection of the semiconductor electronic component plating area in this embodiment is as follows: Figure 3 and Figure 5 The coordinates of the black point ● in the center of the chemical plating area of ​​each semiconductor plating unit are: 4 (14.6, 7.3), 3 (14.6, 21.9), 2 (14.6, 36.5), 1 (14.6, 51.1) in column I; 4 (21.9, 7.3), 3 (21.9, 21.9), 2 (21.9, 36.5), 1 (21.9, 51.1) in column II; 4 (36.5, 7.3), 4 (36.5, 21.9), 2 (36.5, 36.5), 1 (36.5, 51.1) in column III; 4 (51.1, 7.3), 3 (51.1, 21.9), 2 (51.1, 36.5), 1 (51.1, 51.1) in column IV.

[0105] Based on Figure 3 The 3D design drawing of the semiconductor plated part shown has the following chemical plating specifications: 1.5μm≤nickel plating thickness≤3.5μm, and the topmost surface 0.3μm≤platinum plating thickness≤0.7μm. In the following plating thickness data processing of the plated parts, the bottom nickel plating data will not be summarized and discussed, and only the surface platinum plating thickness will be specifically analyzed.

[0106] The thickness of the nickel coating is based on the center value of the design drawing range of 2.5μm, and the thickness of the platinum coating is based on the center value of the design drawing range of 0.5μm. The actual plating treatment is carried out using the chemical plating equipment module.

[0107] The plating conditions are based on the quantity parameters of the platinum chemical plating solution prepared by each component, and the thickness of the coating is calculated and modeled. h 建模厚度 The calculation method is based on the metal platinum electrode potential E (Pt n+ / Pt), the unit is V (volt).

[0108] Its general formula is:

[0109] Pt(IV) → (II)[PtCl6] 2- +2e - =[PtCl4] 2- +2Cl - E = 0.68 V

[0110] Pt(II) → (0)[PtCl4] 2- + 2e - = Pt + 4Cl - E = 0.755 V

[0111] The electrode potential E(B n+ / B), the unit is V (volt).

[0112] B(IV) → (III)[BH ４ ] - —e - →B(OH)3+2H2E = -1.3 V

[0113] The general formula of the chemical reduction reaction is:

[0114] Na2(PtCl6) + Na(BH4) + 6H2O→Pt + B(OH)3+ 6HCl

[0115] In the formula, sodium hexachloroplatinate and sodium borohydride are based on the redox reaction, and the metal ions in the solution are reduced by the strong reducing agent and plated and deposited on the surface of the semiconductor electronic component to obtain the modeled coating thickness. h 建模厚度 .

[0116] The thickness of the electroless platinum-plated samples of semiconductor electronic components was measured using an X-ray film thickness analyzer. h 实测厚度 As shown in Table 2.

[0117] Table 2 Thickness data of electroless platinum plating samples

[0118]

[0119] As can be seen from Table 1, the chemical plating solution of Example 1 is used to perform an actual chemical plating operation on the semiconductor electronic component to be processed through the chemical plating equipment module, and the thickness of the platinum coating obtained is h 实测厚度 The range is 0.505~0.509μm, which is the center value of the design drawing range, that is, the modeled coating thickness h 建模厚度 Compared with 0.5 μm, the coating thickness error is 0.8% to 1.8%, which meets the modeling threshold conditions for the overall quality control threshold of semiconductor electronic components of -5.0% to 5.0%. Therefore, the formula data of the chemical platinum plating solution in Example 1 and its corresponding coating thickness data can be used to construct the RNAS model.

[0120] Furthermore, the thickness of the platinum coating was chemically plated with the chemical plating solution of Example 1 with the additive concentration of 0.5 g / L. h 实测厚度 and modeling coating thickness h 建模厚度The 0.5μm data was processed by the simulation quantity of the computational network of the RNAS model to obtain the simulated data of the reducing agent concentration of the electroless platinum plating solution and the change trend of the electroless platinum plating layer, as shown in Table 3.

[0121] Table 3 Reducing agent concentration and electroless plating platinum coating change trend

[0122]

[0123] The variation trend of the reducing agent concentration of the electroless platinum solution and the error of the simulated platinum coating thickness is obtained by the simulation of the operational equation of the RNAS model. Figure 6 As shown. Figure 6 It can be seen that the modeling thickness is between the reducing agent concentration of 0.5g / L in the simulated chemical plating solution and the additive concentration of 1.0g / L in Example 1. h 建模厚度 The critical point of the discriminant is that the simulated reducing agent concentration of 6.5 g / L is the critical point of the high concentration area.

[0124] In order to confirm the available ratio range of reducing agent concentration of chemical platinum plating solution, the chemical plating solution prepared by using the reducing agent dosage of simulation example 2 and simulation example 8 was prepared based on the component formula of Example 1. The chemical plating equipment module was also used to perform actual chemical plating operation on the semiconductor electronic components to be processed. The thickness of the platinum coating obtained was h 实测厚度 As shown in Table 4.

[0125] Table 4 Measured thickness of platinum coating in simulation examples 2 and 8

[0126]

[0127] From Table 4, we can see that the thickness of the electroless platinum coating of Simulation Example 2 and Simulation Example 8 is h 实测厚度 , and the standard value of modeled coating thickness h 建模厚度 The results of the simulations 2 and 8 were compared with those of the simulations 0.5 μm and did not meet the threshold range. Therefore, the electroless platinum plating solutions of simulations 2 and 8 were classified as unusable formulations.

[0128] Similarly, the chemical plating platinum solutions of simulation examples 3 and 7 were applied to the chemical plating equipment module to perform actual chemical plating operations on the semiconductor plated parts to be processed. The thickness of the chemically plated platinum was obtained. h 实测厚度 As shown in Table 5.

[0129] Table 5 Measured thickness of platinum coating in simulation examples 3 and 7

[0130]

[0131] From Table 4, we can see that the coating thickness of the electroless platinum plating solution of simulation 3 and simulation 7 is h 实测厚度 , which is consistent with the standard value of modeled coating thickness h 建模厚度 Compared with 0.5μm, the film thickness errors are 2.0%~2.6% and 4.4%~5.0% respectively; therefore, the corresponding chemical plating solutions belong to the usable formula.

[0132] In summary, the reducing agent concentrations in all electroless plating solution formulations that meet the morphology threshold range form an orderly available trend range, the results of which are shown in Table 6.

[0133] Table 6 Reducing agent range for electroless platinum plating solution

[0134]

[0135] As can be seen from Table 6, the present invention adopts the computing system of the RNAS model, and the obtained preferred standard for the preparation of the chemical plating solution can achieve accurate and rapid acquisition of the preparation method of the chemical plating solution.

[0136] The preparation of chemical plating solution in the prior art mostly adopts the golden section experimental method, and the actual operation of chemical plating is carried out according to the applicable range of different components. However, when screening the reducing agent concentration, it is necessary to prepare and test samples of each comparative example 1 to 10 with a reducing agent range of 0.5 to 7.5 g / L in order to obtain the corresponding platinum coating thickness and its comparison with the standard value of the management coating thickness. h 管理厚度 The error of 0.5μm is compared, and the results are shown in Table 7.

[0137] Table 7 Relationship between error and additive concentration in Comparative Examples 1 to 10

[0138]

[0139] As can be seen from Table 7, due to the existing chemical plating solution preparation technology, the corresponding coating thickness can only be obtained by actually testing chemical plating samples with various concentrations of reducing agents, and further calculating the platinum coating thickness and its comparison with the standard value of the management coating thickness. h 管理厚度 The error results for comparison are 0.5μm.

[0140] The present invention provides a method and system for constructing an electroless plating solution preparation model based on an RNAS simulation operation and training system. The constructed RNAS model outputs a processing result for electroless plating solution preparation data that meets a threshold range as a "usable recipe," while outputting a processing result for electroless plating solution preparation data that exceeds the threshold range as an "unusable recipe." This standard is used to strictly manage the electroless plating solution preparation process, thereby overcoming the aforementioned shortcomings of the existing electroless plating solution preparation technology and providing high-quality electroless plating solutions for high-end electroless plating equipment modules for semiconductor electronic components. Furthermore, by using the electroless plating film thickness threshold of the semiconductor electronic component to discriminate the measured coating thickness data of the electroless plating equipment module, and using this measured data to simulate the electroless plating solution preparation ratio, the thickness, appearance, color, and overall morphology of the coating after electroless plating of the semiconductor electronic component are monitored, thereby obtaining the optimal standard for the RNAS model for the electroless plating solution preparation model, thereby achieving a method for accurately and quickly obtaining the preparation of the electroless plating solution.

[0141] Some steps in the embodiments of the present invention may be implemented using software, and the corresponding software program may be stored in a readable storage medium, such as a CD or a hard disk.

[0142] 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 scope of protection of the present invention.

Claims

1. A method for constructing a chemical plating solution configuration model, characterized in that: The method comprises: Step 1: Obtain the formula data of the chemical plating solution to be prepared and construct an initial formula data set; Step 2: Obtain the dimension data set of the plated area to be processed and the electrode potential data of the redox strength of the metal to be chemically plated. Calculate the mass of the chemically plated metal according to the general formula of the redox reaction, and calculate the film thickness of the plated model based on the dimension data. h 建模厚度 ; Step 3: Randomly extract chemical plating solution formula data from the initial formula data set, use the chemical plating equipment module to perform actual chemical plating operation on the plated workpiece, and measure the actual film thickness of the plated workpiece h 实测厚度 ; Step 4: Model the film thickness of the plated part h 建模厚度 and the measured film thickness of the plated parts h 实测厚度 Compare them, when the two satisfy the following relationship: h 实测厚度 （100%-5%）≤ h 建模厚度 ≤ h 实测厚度 （100%+5%） Then save the plating thickness of the plated part model h 建模厚度 The corresponding chemical plating solution formula data is used for training the RANS model system; If the above relationship is not satisfied, the chemical plating solution formula data is corrected, and the actual chemical plating operation is performed again using step 3 and the actual film thickness of the plated part is measured. h 实测厚度 ; Until the above relationship is satisfied, the chemical plating solution formula data is saved for RANS model training; Step 5: Model the film thickness of the plated part h 建模厚度 and the measured film thickness of the plated parts h 实测厚度 As input, the RANS model is trained to classify the chemical plating solution formula data, and a classification model for the chemical plating solution formula data is established; The chemical plating solution formula data includes: metal salt, complexing agent, stabilizer, electrolyte, pH regulator and reducing agent; The computing system for RANS model training includes modeling of sensitive condition parameters, and the sensitive condition parameters include: type of chemical plating solution, redox potential of metal ions, redox potential of reducing agent, specific gravity of chemical plating solution, solution temperature, chemical plating time, surface area of ​​plating area, metal density of coating layer and flow rate of chemical plating solution.

2. The method for constructing a chemical plating solution configuration model according to claim 1, wherein: It also includes constructing a set of parameters for the feeling of sudden change, wherein the parameters for the feeling of sudden change include: a tank body, a pump for conveying the chemical plating solution, a length and diameter of a pipeline for conveying the chemical plating solution, semiconductor electronic parts to be processed, and a mold for chemical plating.

3. The method for constructing a chemical plating solution configuration model according to claim 1, wherein: Metal coatings include single metal coatings and alloy coatings.

4. A system for constructing a chemical plating solution configuration model, characterized in that: A method for constructing a chemical plating solution configuration model according to any one of claims 1 to 3, the system comprising: A memory (310) for storing recipe data and thickness data; A data set processing system (200) is used to process the matching relationship between recipe data and thickness data, comprising: an electroless plating reduction plating operation module (210), an electroless plating equipment module (220), an electroless plating film thickness calculation module (230), and a plating film thickness threshold determination module (240); the electroless plating reduction plating operation module (210) is used to obtain recipe parameters and calculate the relationship between the electrode potentials of metal ions and reducing agents in the electroless plating solution; the electroless plating equipment module (220) is used to perform actual electroless plating operations; the electroless plating film thickness calculation module (230) is used to calculate the modeled thickness; and the plating film thickness threshold determination module (240) is used to determine the matching between the modeled thickness and the measured thickness. A RANS model training system (100) is used for training and classifying chemical plating solution formulas.

5. The system for constructing a chemical plating solution configuration model according to claim 4, wherein: The RANS model training system (100) includes: A training module (110) is used for comparative training of the modeled film thickness of the plated part and the measured film thickness of the plated part; a stability generation module (120) for processing the ordered arrangement and trend of the measured coating thickness; A chemical plating reduction component ratio calculation module (130) is used for simulating calculations based on the chemical plating solution ratio corresponding to the measured coating thickness; The model morphology discrimination module (140) is used to discriminate the morphology of the RANS model based on the calculation result of the simulated chemical plating solution formula ratio and its RANS modeling.

6. A method for preparing a chemical plating solution based on a RANS model, characterized in that: The model constructed using the method according to any one of claims 1 to 3 is used to perform recipe identification, comprising: Accurately weigh each component; Keep the concentration of the basic component constant and use the reducing agent as a variable parameter; Calculate the modeled thickness and compare it with the measured thickness; The recipes that meet the threshold conditions are classified and judged through the RANS model.

7. The method for preparing a chemical plating solution according to claim 6, wherein: The RANS model discrimination results include: Available recipes: Modeling thickness data meets the morphology threshold range; Unusable recipe: The modeling thickness data does not meet the topography threshold range.

8. The method for preparing a chemical plating solution according to claim 6, wherein: The film thickness was measured using an X-ray film thickness analyzer.

Images