Semiconductor polishing feedback control method and system

Abstract

The invention provides a feedback control method and system for semiconductor polishing, and relates to the technical field of semiconductor polishing machining.The method comprises the steps that an intelligent feedback device is constructed, and the intelligent feedback device comprises a dot matrix evolution unit, a feedback decision unit and a fuzzy analysis unit; determining a target verification dot matrix in combination with a dot matrix evolution unit; performing polishing control based on the cooperative control scheme, synchronously executing sensing monitoring based on the target verification dot matrix, and determining monitoring feedback data; index matrix group extraction and fuzzy feedback decision making are carried out on the monitoring feedback data, and a feedback control strategy is determined; and receiving a subjective feedback instruction, and executing feedback polishing regulation and control in combination with the feedback control strategy. The technical problems that due to the fact that the processing amount of monitoring data is large and targeted monitoring cannot be achieved, timeliness and accuracy of monitoring feedback are poor, and the polishing quality of the semiconductor is poor can be solved, the pertinence and purposiveness of semiconductor polishing monitoring can be improved, and the technical effect of improving the polishing quality of the semiconductor is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of semiconductor polishing processing, and in particular to a feedback control method and system for semiconductor polishing. Background Art

[0002] Semiconductor polishing is a technology for surface treatment of semiconductor materials, which aims to improve the flatness and smoothness of the surface, thereby laying the foundation for subsequent semiconductor device manufacturing. In order to ensure the quality and efficiency of the polishing process, the polishing process needs to be monitored in real time to promptly detect and deal with possible abnormal situations.

[0003] At present, the existing semiconductor polishing processing methods cannot achieve targeted monitoring due to the large amount of monitoring data processing during the processing, resulting in poor timeliness and accuracy of monitoring feedback, causing technical problems such as poor semiconductor polishing quality. Summary of the invention

[0004] The purpose of this application is to provide a feedback control method and system for semiconductor polishing, so as to solve the technical problem that the existing semiconductor polishing processing method cannot realize targeted monitoring due to the large amount of monitoring data processing during the processing, resulting in poor timeliness and accuracy of monitoring feedback, resulting in poor quality of semiconductor polishing.

[0005] In view of the above problems, the present application provides a feedback control method and system for semiconductor polishing.

[0006] In a first aspect, the present application provides a feedback control method for semiconductor polishing, which is implemented by a feedback control system for semiconductor polishing, wherein the method includes: determining a collaborative control scheme for polishing a target semiconductor in combination with a polishing equipment group, wherein the polishing equipment group includes a polishing robot and auxiliary equipment, and the collaborative control scheme has a synchronization timestamp identifier; constructing an intelligent feedback device, wherein the intelligent feedback device includes a lattice evolution unit, a feedback decision unit and a fuzzy analysis unit, wherein the lattice evolution unit establishes a communication connection with a sensor device group and performs adaptive sensor assistance management; determining a target verification lattice in combination with the lattice evolution unit, in response to the sensor device group, wherein the verification lattice has a phased variable based on the full cycle of the scheme; synchronously executing sensor monitoring based on the target verification lattice along with the periodic dynamic polishing control of the intelligent central control system based on the collaborative control scheme to determine monitoring feedback data; extracting an indicator matrix group and making a fuzzy feedback decision on the monitoring feedback data in combination with the intelligent feedback device to determine a feedback control strategy; connecting a remote human-computer interaction port to receive subjective feedback instructions, and executing feedback polishing regulation of the target semiconductor based on the intelligent central control system in combination with the feedback control strategy.

[0007] In a second aspect, the present application further provides a feedback control system for semiconductor polishing, which is used to execute a feedback control method for semiconductor polishing as described in the first aspect, wherein the system includes: a collaborative control scheme determination module, which is used to determine a collaborative control scheme for polishing a target semiconductor in combination with a polishing equipment group, wherein the polishing equipment group includes a polishing robot and auxiliary equipment, and the collaborative control scheme has a synchronization timestamp identifier; an intelligent feedback device construction module, which is used to construct an intelligent feedback device, wherein the intelligent feedback device includes a lattice evolution unit, a feedback decision unit and a fuzzy analysis unit, and the lattice evolution unit establishes a communication connection with the sensor equipment group to perform adaptive sensor assistance management; a target verification lattice determination module, which is used to determine the target verification lattice determination module The lattice evolution unit determines the target verification lattice in response to the sensor device group, wherein the verification lattice has stage variables based on the full cycle of the scheme; a sensor monitoring module, the sensor monitoring module is used to synchronously perform sensor monitoring based on the target verification lattice along with the periodic dynamic polishing control of the intelligent central control system based on the collaborative control scheme, and determine the monitoring feedback data; a fuzzy feedback decision module, the fuzzy feedback decision module is used to extract the indicator matrix group and make fuzzy feedback decision on the monitoring feedback data in combination with the intelligent feedback device, and determine the feedback control strategy; a feedback polishing control module, the feedback polishing control module is used to connect to the remote human-computer interaction port, receive subjective feedback instructions, and perform feedback polishing control of the target semiconductor based on the intelligent central control system in combination with the feedback control strategy.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] A collaborative control scheme for polishing a target semiconductor is determined by combining a polishing equipment group, wherein the polishing equipment group includes a polishing robot and auxiliary equipment, and the collaborative control scheme has a synchronous timestamp identifier; an intelligent feedback device is constructed, wherein the intelligent feedback device includes a lattice evolution unit, a feedback decision unit and a fuzzy analysis unit, wherein the lattice evolution unit establishes a communication connection with the sensor equipment group to perform adaptive sensor assistance management; a target verification lattice is determined in combination with the lattice evolution unit, and in response to the sensor equipment group, the verification lattice has phase variables based on the full cycle of the scheme; along with the periodic dynamic polishing control based on the collaborative control scheme of the intelligent central control system, sensor monitoring based on the target verification lattice is synchronously performed to determine monitoring feedback data; in combination with the intelligent feedback device, an indicator matrix group is extracted and fuzzy feedback decision is made on the monitoring feedback data to determine a feedback control strategy; a remote human-computer interaction port is connected to receive subjective feedback instructions, and in combination with the feedback control strategy, feedback polishing regulation of the target semiconductor is performed based on the intelligent central control system. That is to say, by combining the polishing equipment group and the surface characteristics and surface quality of the target semiconductor to optimize the polishing scheme, a collaborative control scheme is obtained, which can improve the adaptability and accuracy of the collaborative control scheme setting; then an intelligent feedback device is constructed, which includes a lattice evolution unit, a feedback decision unit and a fuzzy analysis unit; further based on the lattice evolution unit, the target verification lattice is determined, and along with the periodic dynamic polishing control of the intelligent central control system based on the collaborative control scheme, the target semiconductor is synchronously monitored based on the target verification lattice to obtain monitoring feedback data; then through the intelligent feedback device, the indicator matrix group is extracted and fuzzy feedback decision is made on the monitoring feedback data, and the feedback control strategy is output; in addition, the remote human-computer interaction port is connected to receive subjective feedback instructions, and based on the subjective feedback instructions and feedback control strategy, the feedback polishing control of the target semiconductor is executed. It can improve the pertinence and purposefulness of semiconductor polishing monitoring, reduce the amount of monitoring data processing, and thus improve the timeliness and accuracy of monitoring feedback, and timely and accurately control the polishing deviation, and finally achieve the technical effect of improving the quality of semiconductor polishing.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0012] Figure 1 A schematic flow chart of a feedback control method for semiconductor polishing according to the present application;

[0013] Figure 2 A schematic diagram of a flow chart for determining a coordinated control scheme in a feedback control method for semiconductor polishing of the present application;

[0014] Figure 3 This is a schematic structural diagram of a feedback control system for semiconductor polishing in the present application.

[0015] Description of reference numerals:

[0016] Collaborative control scheme determination module 11, intelligent feedback device construction module 12, target verification point array determination module 13, sensor monitoring module 14, fuzzy feedback decision module 15, feedback polishing regulation module 16. DETAILED DESCRIPTION

[0017] This application provides a feedback control method and system for semiconductor polishing, which solves the technical problem that the existing semiconductor polishing processing method cannot realize targeted monitoring due to the large amount of monitoring data processing during the processing, resulting in poor timeliness and accuracy of monitoring feedback, and poor semiconductor polishing quality. It can improve the pertinence and purposefulness of semiconductor polishing monitoring, reduce the amount of monitoring data processing, and thus improve the timeliness and accuracy of monitoring feedback, timely and accurately regulate polishing deviations, and ultimately achieve the technical effect of improving semiconductor polishing quality.

[0018] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0019] Embodiment 1

[0020] Please refer to the attached Figure 1The present application provides a feedback control method for semiconductor polishing, which is applied to a CMP process mode. The method specifically comprises the following steps:

[0021] Step 1: Determine a collaborative control scheme for polishing a target semiconductor in combination with a polishing equipment group, wherein the polishing equipment group includes a polishing robot and auxiliary equipment, and the collaborative control scheme has a synchronization timestamp identifier;

[0022] Specifically, the CMP process, or chemical mechanical polishing, is a key process in the semiconductor manufacturing process. This process achieves efficient removal of excess material on the wafer surface and global nano-level flattening through the synergistic effect of chemical corrosion and mechanical grinding. During the CMP process, the corrosive agent will chemically react with the material surface, dissolving or oxidizing the material surface and removing the uneven parts of the surface. At the same time, the abrasive particles will rub against the material surface, thereby removing the uneven parts and flattening the material surface.

[0023] First, the target semiconductor and polishing equipment group are obtained, wherein the target semiconductor can be set according to the actual situation, and the surface characteristics and surface quality of the target semiconductor are obtained at the same time; the polishing equipment group includes a polishing robot and auxiliary equipment, wherein the polishing robot core polishing equipment has a high degree of automation and intelligent characteristics, through programming and precise control, the polishing robot can continuously and stably perform polishing operations, and the auxiliary equipment includes a liquid sprayer, cooling equipment, etc. Then, based on the surface characteristics, surface quality and the polishing equipment group of the target semiconductor, the polishing control scheme is optimized to obtain a collaborative control scheme, wherein the collaborative control scheme has a synchronous timestamp identifier, and the synchronous timestamp includes a collaborative interaction node and a response delay tolerance time zone based on node accuracy.

[0024] By optimizing the polishing scheme by combining the polishing equipment group and the surface characteristics and surface quality of the target semiconductor, a collaborative control scheme can be obtained, which can improve the adaptability and accuracy of the collaborative control scheme setting, thereby improving the accuracy of the collaborative processing control of the target semiconductor.

[0025] Step 2: construct an intelligent feedback device, which includes a dot matrix evolution unit, a feedback decision unit and a fuzzy analysis unit. The dot matrix evolution unit establishes a communication connection with the sensor device group to perform adaptive sensor assistance management;

[0026] Specifically, an intelligent feedback device is constructed, which is used to monitor the polishing process of the target semiconductor in real time, and to provide timely feedback and control of the abnormal polishing deviation during the monitoring process, wherein the intelligent feedback device includes a lattice evolution unit, a feedback decision unit and a fuzzy analysis unit, wherein the lattice evolution unit is used to optimize the polishing monitoring nodes of the target semiconductor; the feedback decision unit is used to locate the abnormal polishing; the fuzzy analysis unit is used to perform compensation analysis and fuzzy feedback decision based on the abnormal polishing deviation. The lattice evolution unit establishes a communication connection with the sensor device group for performing adaptive sensor-assisted management, and the sensor device group includes a plurality of monitoring sensors for real-time monitoring of the polishing process of the target semiconductor. By constructing an intelligent feedback device, support is provided for the subsequent real-time monitoring and feedback decision of the polishing of the target semiconductor.

[0027] Step 3: Determine a target check point matrix in combination with the point matrix evolution unit, in response to the sensor device group, wherein the check point matrix has phase variables based on the full cycle of the scheme;

[0028] Specifically, the target check lattice is determined based on the lattice evolution unit, and the target check lattice includes a check timestamp and a phased check index, and then the target check lattice is connected to the sensor device group for communication, wherein the check lattice has phased variables based on the full cycle of the scheme, that is, the check lattice includes a check timestamp and a phased check index based on the full cycle of the polishing scheme, and the check timestamp and the phased check index correspond one to one. By determining the target check lattice, a basis is provided for the next step of synchronous sensing monitoring of the full cycle of the target semiconductor polishing process.

[0029] Step 4: Along with the periodic dynamic polishing control based on the collaborative control scheme, the intelligent central control system synchronously performs sensor monitoring based on the target verification point array to determine monitoring feedback data;

[0030] Specifically, the intelligent central control system is a control system that integrates advanced technology and intelligent algorithms to achieve comprehensive monitoring and precise control of the semiconductor polishing process. The system integrates various sensors, actuators, data processing units and communication interfaces to achieve automatic control of polishing equipment, data collection and processing, process optimization and fault diagnosis. Using the intelligent central control system, the target semiconductor is periodically dynamically polished based on the collaborative control scheme, and the full-cycle dynamic polishing of the target semiconductor is synchronously monitored through the target verification point matrix, that is, at each verification timestamp, the monitoring data is compared for deviation based on the phased verification indicators to obtain monitoring feedback data.

[0031] Step 5: Combined with the intelligent feedback device, extract the indicator matrix group and make fuzzy feedback decisions on the monitoring feedback data to determine the feedback control strategy;

[0032] Specifically, the monitoring feedback data is received by the intelligent feedback device, and the feedback decision unit and the fuzzy analysis unit extract the indicator matrix group and make fuzzy feedback decision on the monitoring feedback data. The indicator matrix group is obtained by extracting the monitoring feedback data based on the staged verification indicators; then, the fuzzy feedback decision is made according to the indicator matrix group to obtain the feedback control strategy, which is an optimization and control scheme for the abnormal polishing processing data of the indicator matrix group.

[0033] By extracting sensor monitoring data based on the target verification point matrix, the pertinence and purposefulness of abnormal polishing monitoring can be improved. At the same time, the amount of data processing and the redundancy of data analysis can be reduced, thereby improving the purposefulness, accuracy and efficiency of feedback control.

[0034] Step six: connect to the remote human-computer interaction port, receive subjective feedback instructions, combine the feedback control strategy, and execute feedback polishing regulation of the target semiconductor based on the intelligent central control system.

[0035] Specifically, the remote human-computer interaction port is connected, and the purpose of connecting the remote human-computer interaction port is to connect the local device with the remote user interface to achieve remote control and interaction. Based on the remote human-computer interaction port, a subjective feedback instruction is received, and the subjective feedback instruction refers to a subjective control scheme obtained based on the polishing process deviation analysis; then a comprehensive control analysis is performed based on the subjective feedback instruction and the feedback control strategy, for example: the credibility of the subjective feedback instruction and the feedback control strategy is determined by analysis, and the credibility represents the accuracy of the control, wherein the higher the control accuracy, the higher the credibility; then a weight coefficient is set based on the credibility, and a weighted calculation is performed on the subjective feedback instruction and the feedback control strategy based on the weight coefficient to obtain a comprehensive control scheme; finally, the comprehensive control scheme is fed back to the intelligent central control system, and based on the intelligent central control system, the feedback polishing control of the target semiconductor is performed according to the comprehensive control scheme.

[0036] The feedback control method for semiconductor polishing is applied to a feedback control system for semiconductor polishing, which can solve the technical problem that the existing semiconductor polishing processing method cannot realize targeted monitoring due to the large amount of monitoring data processing during the processing, resulting in poor timeliness and accuracy of monitoring feedback, resulting in poor semiconductor polishing quality. First, a collaborative control scheme for polishing a target semiconductor is determined in combination with a polishing equipment group, wherein the polishing equipment group includes a polishing robot and auxiliary equipment, and the collaborative control scheme has a synchronous timestamp identifier; then, an intelligent feedback device is constructed, wherein the intelligent feedback device includes a lattice evolution unit, a feedback decision unit and a fuzzy analysis unit, wherein the lattice evolution unit establishes a communication connection with the sensor equipment group to perform adaptive sensor assistance management; then, a target verification lattice is determined in combination with the lattice evolution unit, in response to the sensor equipment group, wherein the verification lattice has a phased variable based on the full cycle of the scheme; next, along with the periodic dynamic polishing control of the intelligent central control system based on the collaborative control scheme, sensor monitoring based on the target verification lattice is synchronously performed to determine monitoring feedback data; in addition, in combination with the intelligent feedback device, an indicator matrix group is extracted and a fuzzy feedback decision is made on the monitoring feedback data to determine a feedback control strategy; finally, a remote human-computer interaction port is connected to receive subjective feedback instructions, and in combination with the feedback control strategy, feedback polishing regulation of the target semiconductor is performed based on the intelligent central control system. By combining the polishing equipment group and the surface characteristics and surface quality of the target semiconductor to optimize the polishing scheme, a collaborative control scheme is obtained, which can improve the adaptability and accuracy of the collaborative control scheme setting; then an intelligent feedback device is constructed, which includes a lattice evolution unit, a feedback decision unit and a fuzzy analysis unit; further based on the lattice evolution unit, the target verification lattice is determined, and along with the periodic dynamic polishing control of the intelligent central control system based on the collaborative control scheme, the target semiconductor is synchronously monitored based on the target verification lattice to obtain monitoring feedback data; then through the intelligent feedback device, the indicator matrix group is extracted and fuzzy feedback decision is made on the monitoring feedback data, and the feedback control strategy is output; in addition, the remote human-computer interaction port is connected to receive subjective feedback instructions, and based on the subjective feedback instructions and feedback control strategy, the feedback polishing control of the target semiconductor is executed. It can improve the pertinence and purposefulness of semiconductor polishing monitoring, reduce the amount of monitoring data processing, and thus improve the timeliness and accuracy of monitoring feedback, and timely and accurately control the polishing deviation, and finally achieve the technical effect of improving the quality of semiconductor polishing.

[0037] Further, as attached Figure 2 As shown, step one of this application includes:

[0038] Reading a single polishing plan based on a polishing task, wherein the polishing task is determined based on the surface characteristics and surface quality of the target semiconductor, and the single polishing plan corresponds to the polishing equipment group one by one;

[0039] Determine the interactive nodes of the single polishing solution, identify a synchronization timestamp, wherein the synchronization timestamp has a response delay tolerance time zone based on node accuracy;

[0040] Combined with the single polishing scheme, multi-objective optimization is carried out with collaborative interaction, scheme simplification and quality optimization as target dimensions to determine the collaborative control scheme, wherein the optimization rule is the good-direction iteration and bad-direction fallback of random targets, and the random target is at least one target indicator.

[0041] Specifically, first, a single polishing plan based on a polishing task is read, wherein the polishing task is determined based on the surface characteristics and surface quality of the target semiconductor, the surface characteristics of the semiconductor include characteristics such as surface state binding energy, surface state density, and surface state charge; the surface quality includes parameters such as surface roughness, crystal structure, and surface cleanliness; an expected polishing index is obtained, and then a processing deviation analysis is performed based on the expected polishing index and the surface characteristics and surface quality of the target semiconductor to generate a target polishing task; the target polishing task is further divided according to the polishing equipment group to obtain a plurality of single polishing plans, wherein the single polishing plans correspond one-to-one to the polishing equipment group.

[0042] Identify the interaction nodes of the multiple single polishing schemes, where the interaction nodes refer to the time nodes of the scheme interactions; and based on the interaction node identification synchronization timestamp, further obtain the node accuracy of the interaction node, where the node accuracy can be set according to the importance of the interaction node, where the higher the importance, the greater the node accuracy requirement of the interaction node; then set the response delay tolerance time zone according to the node accuracy, where the response delay tolerance time zone represents the allowable error range of the response delay, and the response delay tolerance time zone is inversely proportional to the node accuracy, that is, the higher the node accuracy requirement, the smaller the corresponding response delay tolerance time zone; finally, embed the response delay tolerance time zone in the corresponding synchronization timestamp.

[0043] Based on the single polishing scheme, a multi-objective optimization of the polishing scheme is performed with collaborative interaction, scheme simplification and quality optimization as target dimensions. The collaborative interaction refers to the smooth communication and cooperation between the polishing equipment group and the intelligent central control system, and the same interaction quality between the polishing equipment groups; the scheme simplification aims to simplify the polishing scheme and reduce the complexity and operation difficulty of the polishing scheme; the quality optimization aims to improve the polishing quality of the target semiconductor; then, a target fitness function is constructed based on the collaborative interaction, scheme simplification and quality optimization. In the target fitness function, the weight proportion of each indicator is different, and the weight can be set according to actual needs. For example, when the polishing quality requirement is large, the weight proportion of the quality optimization is relatively large.

[0044] Based on the target fitness function, the single polishing scheme is optimized by using optimization rules, and the collaborative control scheme is output. The optimization rules are the optimal iteration and inferior fallback of random targets. The optimization rules combine random search, iterative optimization and fallback mechanisms to find the optimal solution to the problem. This strategy is usually used to solve complex problems, where the objective function may have multiple local optimal solutions, or the search space is large and difficult to traverse directly. First, a target is randomly selected, where the random target is at least one target indicator, wherein the randomly selected target means randomly selecting one or more target points as the starting point at the beginning of the search process, which helps to avoid falling into the local optimal solution and increases the possibility of finding the global optimal solution; then, preferential iteration and inferior backoff are performed, wherein preferential iteration means that once the current target point is determined, the algorithm will try to search near the point to find a better solution, which usually involves applying a certain iterative rule or optimization algorithm (such as gradient descent, genetic algorithm, etc.) based on the current point to gradually approach a better solution, wherein the iterative process will continue until a certain stopping condition is reached (such as reaching a preset number of iterations, the quality improvement of the solution is less than a certain threshold, etc.); inferior backoff means that if the quality of the current solution is found to deteriorate (i.e., inferior to the previous solution) during the iteration process, the algorithm will adopt a backoff strategy, which can mean returning to a previous better solution and reselecting the search direction, which helps to avoid falling into the local optimal solution and allows the algorithm to reposition in the search space to find a better solution. This optimization rule combines randomness, iterative optimization and backoff mechanism, which enables the algorithm to strike a balance between exploration and utilization. It can use known information to approach the optimal solution, and avoid falling into the local optimal solution through randomness and backoff. Therefore, this strategy has certain advantages in solving complex optimization problems.

[0045] By optimizing the polishing scheme by combining the polishing equipment group and the surface characteristics and surface quality of the target semiconductor, a collaborative control scheme can be obtained, which can improve the adaptability and accuracy of the collaborative control scheme setting, thereby improving the accuracy of the collaborative processing control of the target semiconductor.

[0046] Further, step 2 of this application includes:

[0047] Identifying surface characteristics of the target semiconductor and determining an initial checkpoint array having a first number of arrays based on a first spacing interval;

[0048] Determine the principle of dot trend change of the calibration dot matrix, in which the dot distribution is adjusted by the staged polishing elements;

[0049] Based on the initial verification lattice and the lattice trend variation principle, supervised training of the lattice evolution unit is performed.

[0050] Specifically, the intelligent feedback device includes a lattice evolution unit. First, the surface characteristics of the target semiconductor are identified and analyzed, which includes observing the external morphological characteristics of the semiconductor, such as particle size, shape, surface flatness, and checking its surface structure, possible defects or impurities, etc. These surface characteristics have a significant impact on the performance and stability of semiconductor devices. For example, particle size and distribution uniformity will affect the electrical and optical properties of the material, and surface defects may cause electron-hole recombination to be blocked, affecting the efficiency of the device; then, an initial verification lattice is constructed according to the identification results. By reasonably arranging the initial verification lattice, it can be ensured that the polishing equipment can accurately position and polish the semiconductor during the processing process, wherein the initial verification lattice has a first lattice number based on a first spacing, that is, there is a verification distance between adjacent verification points, and the initial verification lattice includes multiple verification points.

[0051] Further determine the dot matrix trend change principle of the checkpoint matrix, the dot matrix trend change principle is to adjust the dot matrix distribution according to the stage polishing elements, the stage polishing elements refer to the key verification indicators corresponding to each verification point in the target semiconductor polishing process, and the technicians in this field can set them according to the actual situation; then optimize and adjust the initial checkpoint matrix according to the dot matrix trend change principle, that is, through the distribution of the checkpoints and the changing trend of the number of checkpoints in the whole cycle, determine the checkpoint matrix that meets the stage scenario for the purpose of balancing redundancy and effectiveness. By setting the dot matrix trend change principle to optimize and adjust the initial checkpoint matrix, the precision and accuracy of the target checkpoint matrix setting can be improved, thereby providing a basis for targeted monitoring of semiconductor polishing.

[0052] Furthermore, step 2 of this application also includes:

[0053] Determine the main structure of the fuzzy analysis unit, including a bidirectional fuzzy processing port and a fuzzy reasoning node;

[0054] The bidirectional fuzzy processing port includes a fuzzification direction and a defuzzification direction, the fuzzy reasoning node interacts with the bidirectional fuzzy processing port in a bidirectional manner to form a fuzzy analysis loop, and the fuzzy reasoning node is connected to a reasoning knowledge base;

[0055] Retrieving polishing records of the target semiconductor homologous to the target semiconductor, screening feedback regulation, and determining basic data features and reasoning decision rules as the reasoning knowledge base;

[0056] Based on the polishing record, random samples are screened, supervised training based on the main structure is performed, and the fuzzy analysis unit is determined.

[0057] Specifically, the intelligent feedback device includes a fuzzy analysis unit. First, the main structure of the fuzzy analysis unit is determined, and the main structure includes a bidirectional fuzzy processing port and a fuzzy reasoning node; wherein the bidirectional fuzzy processing port includes a fuzzification direction and a defuzzification direction. First, the processing function of the fuzzification direction is to convert precise polishing parameters or instructions into a fuzzy form. This is because in some cases, due to the complexity of the semiconductor surface or the uncertainty of the polishing equipment, the precise parameters may not fully meet the polishing requirements. Through fuzzification processing, these parameters can be converted into fuzzy values ​​with a certain range or probability distribution to better adapt to changes in the actual polishing process. Among them, fuzzification processing can be based on fuzzy logic or fuzzy set theory. By defining appropriate fuzzy sets and membership functions, precise polishing parameters can be mapped to fuzzy sets and assigned different weights or probabilities. In this way, the polishing system can make decisions and adjustments based on these fuzzy values ​​to adapt to different polishing conditions and requirements; the defuzzification processing function is to convert the fuzzy polishing results or feedback into precise forms. During the polishing process, due to the influence of various factors, the polishing results obtained may be fuzzy or uncertain. The purpose of defuzzification processing is to extract useful information from these fuzzy results and convert them into precise values ​​or conclusions. Among them, defuzzification processing can adopt a variety of methods, such as the central average method, the maximum membership method, etc. These methods determine a most representative precise value based on the membership distribution or other statistical characteristics of the fuzzy results. In this way, the polishing system can perform subsequent operations or adjustments based on the defuzzified results to achieve the expected polishing effect.

[0058] The fuzzy reasoning node interacts with the bidirectional fuzzy processing port in a bidirectional manner to form a fuzzy analysis loop, that is, the fuzzy reasoning node is used as the core component, and its main function is to perform reasoning and calculation based on the input fuzzy information or data through preset fuzzy rules to obtain the corresponding output. These fuzzy rules may involve various parameters, conditions or relationships in the polishing process, which are encoded in the fuzzy reasoning node to guide the reasoning process. The bidirectional fuzzy processing port is responsible for the input and output of fuzzy information. It can convert precise information from external or internal systems into fuzzy information for use by the fuzzy reasoning node; at the same time, it can also convert the output of the fuzzy reasoning node into precise information in order to interact with other systems or devices. This bidirectional interactive feature enables the fuzzy analysis loop to flexibly process various complex and uncertain information, wherein the fuzzy reasoning node is connected to a reasoning knowledge base.

[0059] Further retrieve the polishing records of the target semiconductor homologous to the target semiconductor, that is, obtain the historical polishing records of other semiconductors with the same properties as the target semiconductor; and extract feedback control data from the polishing records to obtain feedback control data; then determine the basic data features and reasoning decision rules based on the feedback control data. First, the feedback control data covers the real-time monitoring data of multiple links in the polishing process, including physical parameters such as polishing force, polishing speed, temperature, humidity, and quality indicators such as surface roughness, flatness, and optical performance; then conduct in-depth analysis of the real-time monitoring data to extract basic data features. This includes pre-processing operations such as cleaning, denoising, and normalization of the data to eliminate the interference of outliers and noise; then use statistical analysis, machine learning and other methods to extract features and reduce dimensions of the data to obtain a data set that can represent the essential characteristics of the polishing process; further formulate reasoning decision rules based on the data set. These rules are formulated based on factors such as polishing goals, process requirements, and empirical knowledge, combined with the relationship and laws between data features. The rules can be expressed as a series of conditional judgment statements or algorithm models to guide parameter adjustment and solution optimization during the polishing process. Finally, an inference knowledge base is constructed based on the basic data features and reasoning decision rules.

[0060] Then, sample training data is randomly screened based on the polishing record, and supervised training is performed on the main structure based on the sample training data to obtain the fuzzy analysis unit that meets the expected training index. The expected training index is an output accuracy index, which can be set according to actual needs.

[0061] Further, step five of this application includes:

[0062] In combination with the lattice evolution unit, the monitoring feedback data is subjected to synchronization verification, and if the verification fails, a first feedback strategy of the time control dimension is generated, wherein the first feedback strategy is identified with feedback equipment and parameter control characteristics;

[0063] If the verification is qualified, extract the index features based on the target verification point matrix, integrate and determine the index matrix group, and the index matrix group corresponds to the target verification point matrix one by one;

[0064] Specifically, the monitoring feedback data is subjected to the extraction of the indicator matrix group and the fuzzy feedback decision. First, in combination with the lattice evolution unit, the monitoring feedback data is subjected to synchronization verification, that is, at each verification timestamp, the monitoring data is extracted and verified based on the expected processing indicators of the verification timestamp to determine whether the monitoring data meets the expected processing indicators. If the monitoring data does not meet the expected processing indicators and the verification is unqualified, a first feedback strategy of the time control dimension is generated, wherein the first feedback strategy is identified with feedback equipment and parameter control features, wherein the feedback equipment is an abnormal polishing equipment, and the parameter control features are control parameters of the abnormal polishing equipment. If the monitoring data meets the expected processing indicators and the verification is qualified, the indicator features of the monitoring data are extracted based on the staged polishing elements of the verification points in the target verification lattice to obtain an indicator matrix group, wherein the indicator matrix group corresponds one-to-one to the target verification lattice.

[0065] Furthermore, the present application also includes the following steps:

[0066] The indicator matrix distribution is established by taking the control deviation dimension as the first indicator multi-group and the polishing quality dimension as the second indicator multi-group;

[0067] Identify the monitoring feedback data and locate the target verification point array;

[0068] In combination with the indicator matrix distribution, the target check lattice is traversed to extract the indicator feature values, integrated and lattice mapping is performed to generate the indicator matrix group.

[0069] Specifically, first, an indicator matrix distribution is constructed with the control deviation dimension as the first indicator multi-group and the polishing quality dimension as the second indicator multi-group; then, the monitoring feedback data is identified, and the target verification point array is located based on the monitoring feedback data, that is, the abnormal verification points of the target verification point array are determined; finally, in combination with the indicator matrix distribution, the indicator feature values ​​of the target verification point array are extracted, and the indicator feature extraction results are subjected to lattice mapping to construct the indicator matrix group.

[0070] By extracting the indicator characteristic values ​​of the monitoring feedback data based on the target verification point matrix, the pertinence and purposefulness of the target semiconductor polishing monitoring can be improved. At the same time, dynamic regulation of the verification point matrix can ensure the compatibility of the verification point matrix with the polishing stage, thereby reducing the amount of monitoring data analysis and processing and improving the efficiency of monitoring data analysis.

[0071] In combination with the feedback decision unit, abnormal polishing positioning is performed based on single-point quality and global fluctuation trend, and the positioning is transferred to the fuzzy analysis unit for regulation and decision-making to determine the feedback control strategy, wherein the abnormal positioning features include abnormal points and abnormal features.

[0072] Specifically, in combination with the feedback decision unit, abnormal polishing positioning is performed based on single-point quality and global fluctuation trend, wherein single-point quality refers to the polishing quality of a single polishing point or area, which is usually evaluated by measuring indicators such as the surface roughness and flatness of the point; the global fluctuation trend refers to the changing trend of quality indicators during the entire polishing process, which reflects the overall stability and consistency of the polishing quality; wherein the abnormal positioning features include abnormal points and abnormal features; and then the abnormal positioning features are transferred to the fuzzy analysis unit for regulation and decision-making, and a feedback control strategy is output, and the feedback control strategy is an optimization scheme for abnormal polishing positioning.

[0073] Furthermore, step six of this application includes:

[0074] Determining a self-feedback control module of the polishing robot, wherein the self-feedback control module is connected to a force feedback sensor installed on the organism;

[0075] Establish a collaborative association between the self-feedback control module and the intelligent feedback device.

[0076] Specifically, first, the self-feedback control module of the polishing robot is determined, wherein the self-feedback control module refers to automatically adjusting the system parameters and control strategies by collecting and analyzing the difference between the system output and the expected target in real time to achieve precise control of the polishing process; wherein the self-feedback control module is connected to the force feedback sensor assembled by the organism, and the force feedback sensor is the core component of the self-feedback control module, which can detect the magnitude and direction of the force applied by the polishing robot on the semiconductor surface in real time, and transmit this information to the self-feedback control module, and this real-time force feedback mechanism enables the polishing robot to flexibly adjust the magnitude and distribution of the applied force according to the real-time processing situation to adapt to different polishing requirements and conditions; that is, after the self-feedback control module receives the information from the force feedback sensor, it will perform a series of calculations and analyses, and compare the difference between the real-time detected force and the ideal value according to the preset polishing parameters and process requirements, and adjust the parameters such as the motion trajectory, speed and strength of the polishing robot accordingly. This real-time feedback and control mechanism enables the polishing robot to maintain a stable processing state during the polishing process and improve the polishing quality and efficiency. Finally, a collaborative association between the self-feedback control module and the intelligent feedback device is established, wherein the collaborative association can ensure that the self-feedback control module and the intelligent feedback device can interact and share information in real time during the polishing process, and jointly optimize polishing parameters and strategies.

[0077] In summary, the feedback control method for semiconductor polishing provided by the present application has the following technical effects:

[0078] 1. By combining the polishing equipment group and the surface characteristics and surface quality of the target semiconductor to optimize the polishing scheme, a collaborative control scheme is obtained, which can improve the adaptability and accuracy of the collaborative control scheme setting; then an intelligent feedback device is constructed, which includes a lattice evolution unit, a feedback decision unit and a fuzzy analysis unit; further based on the lattice evolution unit, the target verification lattice is determined, and along with the periodic dynamic polishing control of the intelligent central control system based on the collaborative control scheme, the target semiconductor is synchronously monitored based on the target verification lattice to obtain monitoring feedback data; then through the intelligent feedback device, the indicator matrix group is extracted and fuzzy feedback decision is made on the monitoring feedback data, and the feedback control strategy is output; in addition, the remote human-computer interaction port is connected to receive subjective feedback instructions, and based on the subjective feedback instructions and feedback control strategy, the feedback polishing control of the target semiconductor is executed. It can improve the pertinence and purposefulness of semiconductor polishing monitoring, reduce the amount of monitoring data processing, and thus improve the timeliness and accuracy of monitoring feedback, and timely and accurately control the polishing deviation, and finally achieve the technical effect of improving the quality of semiconductor polishing.

[0079] 2. By extracting sensor monitoring data based on the target verification point matrix, the pertinence and purposefulness of abnormal polishing monitoring can be improved. At the same time, the amount of data processing can be reduced, and the redundancy of data analysis can be reduced, thereby improving the purposefulness, accuracy and efficiency of feedback control.

[0080] Embodiment 2

[0081] Based on the same inventive concept as the feedback control method for semiconductor polishing in the aforementioned embodiment, the present application also provides a feedback control system for semiconductor polishing, see the attached Figure 3 , the system comprising:

[0082] A collaborative control scheme determination module 11, the collaborative control scheme determination module 11 is used to determine a collaborative control scheme for polishing a target semiconductor in combination with a polishing equipment group, the polishing equipment group includes a polishing robot and auxiliary equipment, and the collaborative control scheme has a synchronization timestamp identifier;

[0083] An intelligent feedback device construction module 12, the intelligent feedback device construction module 12 is used to construct an intelligent feedback device, the intelligent feedback device includes a dot matrix evolution unit, a feedback decision unit and a fuzzy analysis unit, the dot matrix evolution unit establishes a communication connection with the sensor device group, and performs adaptive sensor assistance management;

[0084] a target check point matrix determining module 13, the target check point matrix determining module 13 is used to determine a target check point matrix in combination with the point matrix evolution unit, in response to the sensor device group, wherein the check point matrix has a phased variable based on the full cycle of the scheme;

[0085] A sensor monitoring module 14, which is used to synchronously perform sensor monitoring based on the target verification point array and determine monitoring feedback data along with the periodic dynamic polishing control of the intelligent central control system based on the collaborative control scheme;

[0086] A fuzzy feedback decision module 15, which is used to extract an indicator matrix group and make a fuzzy feedback decision on the monitoring feedback data in combination with the intelligent feedback device, and determine a feedback control strategy;

[0087] The feedback polishing control module 16 is used to connect to a remote human-computer interaction port, receive subjective feedback instructions, and perform feedback polishing control of the target semiconductor based on the intelligent central control system in combination with the feedback control strategy.

[0088] Furthermore, the collaborative control scheme determination module 11 in the system is also used for:

[0089] Reading a single polishing plan based on a polishing task, wherein the polishing task is determined based on the surface characteristics and surface quality of the target semiconductor, and the single polishing plan corresponds to the polishing equipment group one by one;

[0090] Determine the interactive nodes of the single polishing solution, identify a synchronization timestamp, wherein the synchronization timestamp has a response delay tolerance time zone based on node accuracy;

[0091] Combined with the single polishing scheme, multi-objective optimization is carried out with collaborative interaction, scheme simplification and quality optimization as target dimensions to determine the collaborative control scheme, wherein the optimization rule is the good-direction iteration and bad-direction fallback of random targets, and the random target is at least one target indicator.

[0092] Furthermore, the intelligent feedback device building module 12 in the system is also used for:

[0093] Identifying surface characteristics of the target semiconductor and determining an initial checkpoint array having a first number of arrays based on a first spacing interval;

[0094] Determine the principle of dot trend change of the calibration dot matrix, in which the dot distribution is adjusted by the staged polishing elements;

[0095] Based on the initial verification lattice and the lattice trend variation principle, supervised training of the lattice evolution unit is performed.

[0096] Furthermore, the intelligent feedback device building module 12 in the system is also used for:

[0097] Determine the main structure of the fuzzy analysis unit, including a bidirectional fuzzy processing port and a fuzzy reasoning node;

[0098] The bidirectional fuzzy processing port includes a fuzzification direction and a defuzzification direction, the fuzzy reasoning node interacts with the bidirectional fuzzy processing port in a bidirectional manner to form a fuzzy analysis loop, and the fuzzy reasoning node is connected to a reasoning knowledge base;

[0099] Retrieving polishing records of the target semiconductor homologous to the target semiconductor, screening feedback regulation, and determining basic data features and reasoning decision rules as the reasoning knowledge base;

[0100] Based on the polishing record, random samples are screened, supervised training based on the main structure is performed, and the fuzzy analysis unit is determined.

[0101] Furthermore, the fuzzy feedback decision module 15 in the system is also used for:

[0102] In combination with the lattice evolution unit, the monitoring feedback data is subjected to synchronization verification, and if the verification fails, a first feedback strategy of the time control dimension is generated, wherein the first feedback strategy is identified with feedback equipment and parameter control characteristics;

[0103] If the verification is qualified, extract the index features based on the target verification point matrix, integrate and determine the index matrix group, and the index matrix group corresponds to the target verification point matrix one by one;

[0104] In combination with the feedback decision unit, abnormal polishing positioning is performed based on single-point quality and global fluctuation trend, and the positioning is transferred to the fuzzy analysis unit for regulation and decision-making to determine the feedback control strategy, wherein the abnormal positioning features include abnormal points and abnormal features.

[0105] Furthermore, the fuzzy feedback decision module 15 in the system is also used for:

[0106] The indicator matrix distribution is established by taking the control deviation dimension as the first indicator multi-group and the polishing quality dimension as the second indicator multi-group;

[0107] Identify the monitoring feedback data and locate the target verification point array;

[0108] In combination with the indicator matrix distribution, the target check lattice is traversed to extract the indicator feature values, integrated and lattice mapping is performed to generate the indicator matrix group.

[0109] Furthermore, the feedback polishing control module 16 in the system is also used for:

[0110] Determining a self-feedback control module of the polishing robot, wherein the self-feedback control module is connected to a force feedback sensor installed on the organism;

[0111] Establish a collaborative association between the self-feedback control module and the intelligent feedback device.

[0112] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The feedback control method and specific examples of a semiconductor polishing in the aforementioned embodiment 1 are also applicable to a feedback control system of a semiconductor polishing in this embodiment. Through the aforementioned detailed description of a feedback control method of a semiconductor polishing, those skilled in the art can clearly understand the feedback control system of a semiconductor polishing in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0113] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0114] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A feedback control method for semiconductor polishing, characterized in that: Applied to the CMP process mode, the method comprises: Determine a collaborative control scheme for polishing a target semiconductor in combination with a polishing equipment group, the polishing equipment group including a polishing robot and auxiliary equipment, the collaborative control scheme having a synchronization timestamp identifier; Constructing an intelligent feedback device, the intelligent feedback device includes a dot matrix evolution unit, a feedback decision unit and a fuzzy analysis unit, the dot matrix evolution unit establishes a communication connection with the sensor device group to perform adaptive sensor assistance management; determining a target check lattice in conjunction with the lattice evolution unit, in response to the sensor device group, wherein the check lattice has phased variables based on the full cycle of the scheme; Along with the periodic dynamic polishing control based on the collaborative control scheme of the intelligent central control system, the sensor monitoring based on the target verification point array is synchronously performed to determine the monitoring feedback data; In combination with the intelligent feedback device, the monitoring feedback data is subjected to the extraction of the indicator matrix group and the fuzzy feedback decision, and the feedback control strategy is determined; Connecting to a remote human-computer interaction port, receiving subjective feedback instructions, combining the feedback control strategy, and executing feedback polishing regulation of the target semiconductor based on the intelligent central control system.

2. The method according to claim 1, characterized in that The collaborative control scheme for determining the target semiconductor for polishing includes: Reading a single polishing plan based on a polishing task, wherein the polishing task is determined based on the surface characteristics and surface quality of the target semiconductor, and the single polishing plan corresponds to the polishing equipment group one by one; Determine the interactive nodes of the single polishing solution, identify a synchronization timestamp, wherein the synchronization timestamp has a response delay tolerance time zone based on node accuracy; Combined with the single polishing scheme, multi-objective optimization is carried out with collaborative interaction, scheme simplification and quality optimization as target dimensions to determine the collaborative control scheme, wherein the optimization rule is the good-direction iteration and bad-direction fallback of random targets, and the random target is at least one target indicator.

3. The method according to claim 1, characterized in that The intelligent feedback device includes a dot matrix evolution unit, including: Identifying surface characteristics of the target semiconductor and determining an initial checkpoint array having a first number of arrays based on a first spacing interval; Determine the principle of dot trend change of the calibration dot matrix, in which the dot distribution is adjusted by the staged polishing elements; Based on the initial verification lattice and the lattice trend variation principle, supervised training of the lattice evolution unit is performed.

4. The method according to claim 1, characterized in that The intelligent feedback device comprises a fuzzy analysis unit, including: Determine the main structure of the fuzzy analysis unit, including a bidirectional fuzzy processing port and a fuzzy reasoning node; The bidirectional fuzzy processing port includes a fuzzification direction and a defuzzification direction, the fuzzy reasoning node interacts with the bidirectional fuzzy processing port in a bidirectional manner to form a fuzzy analysis loop, and the fuzzy reasoning node is connected to a reasoning knowledge base; Retrieving polishing records of the target semiconductor homologous to the target semiconductor, screening feedback regulation, and determining basic data features and reasoning decision rules as the reasoning knowledge base; Based on the polishing record, random samples are screened, supervised training based on the main structure is performed, and the fuzzy analysis unit is determined.

5. The method according to claim 1, characterized in that Extracting the indicator matrix group and making fuzzy feedback decisions on the monitoring feedback data include: In combination with the lattice evolution unit, the monitoring feedback data is subjected to synchronization verification, and if the verification fails, a first feedback strategy of the time control dimension is generated, wherein the first feedback strategy is identified with feedback equipment and parameter control characteristics; If the verification is qualified, extract the index features based on the target verification point matrix, integrate and determine the index matrix group, and the index matrix group corresponds to the target verification point matrix one by one; In combination with the feedback decision unit, abnormal polishing positioning is performed based on single-point quality and global fluctuation trend, and the positioning is transferred to the fuzzy analysis unit for regulation and decision-making to determine the feedback control strategy, wherein the abnormal positioning features include abnormal points and abnormal features.

6. The method according to claim 5, characterized in that The indicator matrix distribution is established by taking the control deviation dimension as the first indicator multi-group and the polishing quality dimension as the second indicator multi-group; Identify the monitoring feedback data and locate the target verification point array; In combination with the indicator matrix distribution, the target check lattice is traversed to extract the indicator feature values, integrated and lattice mapping is performed to generate the indicator matrix group.

7. The method according to claim 1, characterized in that include: Determining a self-feedback control module of the polishing robot, wherein the self-feedback control module is connected to a force feedback sensor installed on the organism; Establish a collaborative association between the self-feedback control module and the intelligent feedback device.

8. A feedback control system for semiconductor polishing, characterized in that: For implementing the steps of the method according to any one of claims 1 to 7, the system comprises: A collaborative control scheme determination module, the collaborative control scheme determination module is used to determine a collaborative control scheme for polishing a target semiconductor in combination with a polishing equipment group, the polishing equipment group includes a polishing robot and auxiliary equipment, and the collaborative control scheme has a synchronization timestamp identifier; An intelligent feedback device construction module, wherein the intelligent feedback device construction module is used to construct an intelligent feedback device, wherein the intelligent feedback device comprises a dot matrix evolution unit, a feedback decision unit and a fuzzy analysis unit, wherein the dot matrix evolution unit establishes a communication connection with a sensor device group to perform adaptive sensor assistance management; a target check point matrix determination module, the target check point matrix determination module being used to determine a target check point matrix in combination with the point matrix evolution unit, in response to the sensor device group, wherein the check point matrix has a phased variable based on a full cycle of the scheme; A sensor monitoring module, which is used to synchronously perform sensor monitoring based on the target verification point array and determine monitoring feedback data along with the periodic dynamic polishing control of the intelligent central control system based on the collaborative control scheme; A fuzzy feedback decision module, which is used to extract the indicator matrix group and make fuzzy feedback decisions on the monitoring feedback data in combination with the intelligent feedback device to determine the feedback control strategy; A feedback polishing control module is used to connect to a remote human-computer interaction port, receive subjective feedback instructions, and perform feedback polishing control of the target semiconductor based on the intelligent central control system in combination with the feedback control strategy.

Images