Monitoring method for crystal pulling process of single crystal furnace, electronic equipment, medium and program product

Abstract

The invention belongs to the technical field of monocrystalline silicon production, and particularly relates to a monitoring method for a crystal pulling process of a single crystal furnace, electronic equipment, a medium and a program product. Environmental information of a current crystal pulling process is determined, a prediction model matched with the environmental information is obtained, production parameters of all working steps in the current crystal pulling process are input into the prediction model, a prediction result output by the prediction model is obtained, and the prediction result is used for indicating whether abnormity exists or not and an abnormity type under the abnormal condition. And / or the prediction model is used for indicating a production parameter adjustment strategy, and the prediction model is obtained based on historical environment information corresponding to a historical crystal pulling process and historical production parameters of each process step; the method effectively improves the monitoring accuracy of the crystal pulling process of the single crystal furnace.

Description

Technical Field

[0001] The present application relates to the technical field of single crystal silicon production, and particularly relates to a monitoring method for the crystal pulling process of a single crystal furnace, an electronic device, a medium, and a program product. Background Art

[0002] The crystal pulling process of a single crystal furnace is the core process for preparing key materials such as single crystal silicon in the semiconductor manufacturing field. Due to its regular atomic arrangement and excellent electrical properties, single crystal silicon has become an essential basic material for many electronic devices such as integrated circuits and solar cells. During the crystal pulling process of a single crystal furnace, high-purity polysilicon raw materials need to be melted into a liquid state in a high-temperature environment, and then a seed crystal with a specific crystal orientation is immersed in the melt and slowly pulled up. At the same time, key parameters such as temperature, pulling speed, and rotation speed are precisely controlled to enable the melt to crystallize and grow orderly on the surface of the seed crystal, and finally obtain a single crystal silicon rod with a regular geometric shape and excellent electrical properties. The fineness of this process directly determines the quality and performance of single crystal silicon, and thus affects the yield and reliability of electronic devices.

[0003] In the traditional crystal pulling process of a single crystal furnace, practitioners mainly rely on manual experience to discover and solve problems. The crystal pulling production involves many complex technological processes and parameters. When an abnormal situation occurs, based on years of accumulated experience, the staff can roughly judge the problem and take corresponding solutions.

[0004] However, for most ordinary practitioners, it is difficult to analyze these complex and scattered data. Therefore, at present, it is difficult to obtain accurate and reliable results for the monitoring of the crystal pulling process of a single crystal furnace, and the monitoring accuracy is relatively low. Summary of the Invention

[0005] Embodiments of the present application provide a monitoring method for the crystal pulling process of a single crystal furnace, an electronic device, a medium, and a program product, so as to solve the problem of relatively low monitoring accuracy of the crystal pulling process of a single crystal furnace.

[0006] In a first aspect, embodiments of the present application provide a monitoring method for the crystal pulling process of a single crystal furnace, including:

[0007] Determine the environmental information of the current crystal pulling process, and obtain a prediction model that matches the environmental information;

[0008] Input the production parameters of each process step in the current crystal pulling process into the prediction model to obtain a prediction result output by the prediction model. The prediction result is used to indicate whether there is an abnormality and the type of abnormality in the case of an abnormality, and / or is used to indicate a production parameter adjustment strategy, where the prediction model is obtained based on the historical environmental information corresponding to the historical crystal pulling process and the historical production parameters of each process step.

[0009] In an alternative embodiment, the prediction model includes a classification model and a regression model, and the prediction results include a first prediction result and a second prediction result;

[0010] Input the production parameters of each process step in the current crystal pulling process into the classification model to obtain a first prediction result, which is used to indicate whether there is an abnormality and the type of abnormality in the case of an abnormality;

[0011] Input the production parameters of each process step in the current crystal pulling process into the regression model to obtain a second prediction result, which is used to indicate the control parameter adjustment strategy.

[0012] In an alternative embodiment, the environmental information includes at least one of raw materials, auxiliary materials, thermal field, and crucible.

[0013] In an alternative embodiment, it further includes:

[0014] Obtain multiple data such as furnace platform data, quality data, production capacity data, process step time, and auxiliary material information in the crystal pulling process respectively. According to the time series of each data item, associate the furnace platform data, quality data, production capacity data, process step time, and auxiliary material information corresponding to the time, and generate a globally unique identifier for each obtained associated data. The associated data includes the production parameters and the environmental information.

[0015] In an alternative embodiment, the obtaining multiple data such as furnace platform data, quality data, production capacity data, process step time, and auxiliary material information in the crystal pulling process respectively includes:

[0016] Obtain the furnace platform data from the single crystal furnace centralized control system;

[0017] Obtain the quality data and the production capacity data from the production management system;

[0018] Obtain the process step time from the working hours system;

[0019] Obtain the auxiliary material information from the material system.

[0020] In an alternative embodiment, it further includes:

[0021] According to the user's permission, display some or all of the data in the associated data through a visualization page.

[0022] In an alternative embodiment, it further includes:

[0023] In response to an operation on some of the associated data, display other data in the associated data on the visualization page.

[0024] Second aspect, an embodiment of the present application provides a monitoring device for the single crystal pulling process of a single crystal furnace, including:

[0025] A determination module, configured to determine the environmental information of the current single crystal pulling process;

[0026] An acquisition module, configured to acquire a prediction model that matches the environmental information;

[0027] The determination module is further configured to input the production parameters of each process step in the current single crystal pulling process into the prediction model, and obtain a prediction result output by the prediction model. The prediction result is used to indicate whether there is an abnormality and the type of abnormality in the case of an abnormality, and / or is used to indicate a production parameter adjustment strategy, where the prediction model is obtained based on the historical environmental information corresponding to the historical single crystal pulling process and the historical production parameters of each process step.

[0028] In an optional implementation manner, the determination module is further configured to input the production parameters of each process step in the current single crystal pulling process into the classification model, and obtain a first prediction result. The first prediction result is used to indicate whether there is an abnormality and the type of abnormality in the case of an abnormality;

[0029] The determination module is further configured to input the production parameters of each process step in the current single crystal pulling process into the regression model, and obtain a second prediction result. The second prediction result is used to indicate a control parameter adjustment strategy.

[0030] In an optional implementation manner, the determination module is further configured to the environmental information includes at least one of raw materials, auxiliary materials, thermal field, and crucible.

[0031] In an optional implementation manner, the acquisition module is further configured to respectively acquire multiple data such as furnace platform data, quality data, production capacity data, process step time, and auxiliary material information during the single crystal pulling process;

[0032] The determination module is further configured to correlate the furnace platform data, quality data, production capacity data, process step time, and auxiliary material information corresponding to the time according to the time series of each item of data, and generate a globally unique identifier for each obtained associated data. The associated data includes the production parameters and the environmental information.

[0033] In an optional implementation manner, the acquisition module is further configured to acquire the furnace platform data from the single crystal furnace centralized control system;

[0034] The acquisition module is further configured to acquire the quality data and the production capacity data from the production management system;

[0035] The acquisition module is further configured to acquire the process step time from the man-hour system;

[0036] The obtaining module is further configured to obtain the auxiliary material information from the material system.

[0037] In an alternative embodiment, the monitoring device for the single crystal furnace crystal pulling process further includes: a processing module;

[0038] The processing module is further configured to display some or all of the associated data through a visualization page according to the user permissions.

[0039] In an alternative embodiment, the processing module is further configured to, in response to an operation on some of the associated data, display other data in the associated data on the visualization page.

[0040] In a third aspect, an embodiment of the present application provides a monitoring device for the single crystal furnace crystal pulling process, including: a memory, a processor;

[0041] The memory stores computer-executable instructions;

[0042] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementation manners of the first aspect.

[0043] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, they are used to implement the above first aspect and / or various possible implementation manners of the first aspect.

[0044] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the above first aspect and / or various possible implementation manners of the first aspect.

[0045] The monitoring method for the single crystal furnace crystal pulling process provided by the embodiment of the present application determines the environmental information of the current crystal pulling process, obtains a prediction model matching the environmental information, inputs the production parameters of each process step in the current crystal pulling process into the prediction model, and obtains a prediction result output by the prediction model. The prediction result is used to indicate whether there is an abnormality and the type of abnormality in the case of an abnormality, and / or is used to indicate a production parameter adjustment strategy, where the prediction model is obtained based on the historical environmental information corresponding to the historical crystal pulling process and the historical production parameters of each process step; this method effectively improves the monitoring accuracy of the single crystal furnace crystal pulling process. Description of the Drawings

[0046] The accompanying drawings here are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0047] Figure 1 Flow chart of the monitoring method for the single crystal pulling process of the present application

[0048] Figure 2 Structural schematic diagram of the monitoring device for the single crystal pulling process of the present application

[0049] Figure 3 Structural schematic diagram of the monitoring equipment for the single crystal pulling process of the present application

[0050] Through the above - mentioned drawings, specific embodiments of the present application have been shown, and there will be a more detailed description hereinafter. These drawings and textual descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments Detailed implementation manners

[0051] Here, the exemplary embodiments will be described in detail, and examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims

[0052] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties. And the collection, use, and processing of relevant data need to comply with relevant laws, regulations, and standards, and corresponding operation entrances are provided for users to choose to authorize or refuse

[0053] The single crystal pulling process in a single crystal furnace is the core process for preparing key materials such as single - crystal silicon in the field of semiconductor manufacturing. As the basic material for many electronic devices such as integrated circuits and solar cells. The single crystal pulling process in a single crystal furnace requires melting high - purity polysilicon raw materials into a liquid state under high - temperature conditions, and by immersing a seed crystal with a specific crystal orientation into the melt and slowly pulling it up, precisely controlling parameters such as temperature, pulling speed, and rotation speed to promote the orderly crystallization growth of the melt on the surface of the seed crystal, thereby forming a high - quality single - crystal silicon rod. The fineness of this process directly determines the quality and performance of the final product, and is crucial for the yield and reliability of electronic devices

[0054] During the traditional single-crystal furnace crystal pulling process, workers mainly rely on personal experience to identify and solve problems. Since the crystal pulling production involves complex technological processes and multiple parameters, when encountering abnormal situations, experienced employees can roughly judge the problem based on past experience and take corresponding measures to solve it.

[0055] However, for most ordinary practitioners, analyzing these complex and scattered data poses great challenges. Therefore, it is difficult to obtain accurate and reliable results in the current monitoring of the single-crystal furnace crystal pulling process, and the monitoring accuracy is relatively low.

[0056] To address the above problems, the monitoring method for the single-crystal furnace crystal pulling process provided in this application first determines the environmental information of the current crystal pulling process, trains a prediction model adapted to the environmental information based on the historical environmental information corresponding to the historical crystal pulling process and the historical production parameters of each process step, then obtains the prediction model that matches the current environmental information, inputs the production parameters of each process step of the current crystal pulling process into the model, and uses the internal rules learned by the model from a large amount of historical data to output a prediction result to indicate whether there is an abnormality, the type of abnormality, and / or the production parameter adjustment strategy, thereby improving the monitoring accuracy of the single-crystal furnace crystal pulling process.

[0057] The following uses specific embodiments to detail the technical solutions of this application and how the technical solutions of this application solve the above technical problems. These several specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0058] Figure 1 is the flow of the monitoring method for the single-crystal furnace crystal pulling process provided in this application Figure 1 . The execution subject of this embodiment is, for example, a monitoring system for the single-crystal furnace crystal pulling process. As Figure 1 shown, the monitoring method for the single-crystal furnace crystal pulling process shown in this embodiment includes:

[0059] S101: Determine the environmental information of the current crystal pulling process and obtain a prediction model that matches the environmental information.

[0060] Among them, the environmental information in the crystal pulling process refers to the parameters that have a key impact on the crystal growth quality, including precisely controlled temperature fields to ensure uniform heat distribution and stable growth rates, an inert gas (such as argon) environment to prevent material oxidation and reaction with air components, appropriate pressure conditions to maintain the stability of the atmosphere and prevent impurity intrusion, and reduction of external vibration interference to ensure the integrity of the crystal structure. The environmental factors work together to ensure the accuracy of industrial data and the efficiency of crystal growth during the crystal pulling process.

[0061] The prediction model is a mathematical tool that combines historical data with real-time environmental information. It aims to simulate and predict the possible states or outcomes during the crystal pulling process by analyzing key environmental factors such as temperature distribution, atmosphere composition, pressure conditions, etc. This model is constructed using machine learning algorithms, statistical methods, or physical simulation platforms, which can identify the complex interrelationships among environmental variables and predict crystal growth quality, defect risks, or process optimization directions accordingly. Through high-precision, multi-dimensional, and time-series synchronized data input, it enables early judgment and control of the dynamic changes during the production process, thereby improving product quality and production efficiency.

[0062] It can be understood that by real-time detecting and collecting data on the key environmental parameters (such as temperature distribution, atmosphere composition, pressure level, vibration intensity, etc.) that affect crystal growth during the crystal pulling process, the environmental state of the current process can be determined. Based on this, combined with the pre-constructed prediction model library, a mathematical model that can reflect the characteristics of this environment is selected or adjusted for simulating and predicting crystal growth behavior and quality trends. This matching process ensures the consistency between the model input and the actual working conditions, thereby improving the accuracy and practicality of the prediction results.

[0063] S102: Input the production parameters of each step in the current crystal pulling process into the prediction model to obtain the prediction result output by the prediction model. The prediction result is used to indicate whether there is an abnormality and the type of abnormality in case of an abnormality, and / or, is used to indicate the production parameter adjustment strategy, where the prediction model is obtained based on the historical environmental information corresponding to the historical crystal pulling process and the historical production parameters of each step.

[0064] Inputting the production parameters corresponding to each step in the current crystal pulling process into the pre-constructed prediction model is a key step in realizing the detection and optimization of crystal growth quality. In actual operation, first, it is necessary to collect in real-time the environmental information (such as temperature, atmosphere composition, pressure conditions, etc.) and specific production parameters (such as pulling speed, power setting, etc.) of each step through devices such as sensors. Once these data are collected, they will be used as inputs and sent into the prediction model for analysis.

[0065] After receiving these input data, the prediction model will go through a series of complex calculation and analysis processes. During this process, the model analyzes these data according to its internal algorithm and compares them with a large number of samples in the historical database. By matching the newly input data with the historical data patterns, the model can identify whether there are potential problems in the current production environment.

[0066] The prediction results can not only determine whether there are abnormal conditions in the current crystal pulling process, but also further clarify the specific types of abnormalities. For example, if it is found that the crystal growth is uneven, it may indicate a problem with improper temperature control; while if an increase in crystal defects is detected, it may be due to unreasonable adjustment of the pulling speed. In addition, the prediction results also provide production parameter adjustment strategies for specific abnormalities. These suggestions may involve specific measures such as fine-tuning the temperature setting value, appropriately increasing or decreasing the pulling speed, etc., aiming to help production personnel respond quickly, optimize the production process, and improve product quality and consistency.

[0067] The monitoring method for the crystal pulling process of the single crystal furnace provided in this embodiment determines the environmental information of the current crystal pulling process, obtains a prediction model that matches the environmental information, inputs the production parameters of each process step in the current crystal pulling process into the prediction model, and obtains the prediction results output by the prediction model. The prediction results are used to indicate whether there are abnormalities and the types of abnormalities in case of abnormalities, and / or are used to indicate the production parameter adjustment strategy, where the prediction model is obtained based on the historical environmental information corresponding to the historical crystal pulling process and the historical production parameters of each process step; this method effectively improves the monitoring accuracy of the crystal pulling process of the single crystal furnace.

[0068] In a possible implementation manner, the prediction model includes a classification model and a regression model, and the prediction results include a first prediction result and a second prediction result;

[0069] Input the production parameters of each process step in the current crystal pulling process into the classification model to obtain a first prediction result, and the first prediction result is used to indicate whether there are abnormalities and the types of abnormalities in case of abnormalities;

[0070] Input the production parameters of each process step in the current crystal pulling process into the regression model to obtain a second prediction result, and the second prediction result is used to indicate the control parameter adjustment strategy.

[0071] In the crystal pulling production prediction system, the constructed prediction model is not a single structure, but is jointly composed of a classification model and a regression model. These two models each undertake unique functions and work together to achieve accurate prediction and effective guidance for the crystal pulling process. The classification model and the regression model are based on different algorithm principles and are modeled for different types of targets in crystal pulling production, so as to provide comprehensive and targeted information for production personnel.

[0072] The classification model mainly focuses on judging whether there are any abnormalities in the crystal pulling process and the types of abnormalities. In actual operation, the production parameters corresponding to each process step in the current crystal pulling process are used as input data and transmitted to the classification model. Based on the historical data patterns and rules learned in advance, the classification model analyzes and processes these input parameters. After a series of complex calculations and logical judgments, the model outputs the first prediction result. This result can indicate to the production personnel whether there are any abnormal conditions in the current crystal pulling process. If there are abnormalities, it can further point out the specific types of abnormalities, such as crystal growth abnormalities caused by too high or too low temperature, or crystal defects caused by unstable pulling speed, etc.

[0073] The regression model focuses on providing strategic suggestions for adjusting the control parameters of the crystal pulling process. Similarly, the production parameters of each process step in the current crystal pulling process are input into the regression model. The regression model analyzes and models the relationship between these parameters and the target control parameters, and calculates the corresponding adjustment amount. The final output second prediction result is presented in the form of specific numerical values or adjustment ranges, providing clear production parameter adjustment strategies for the production personnel. For example, the model may suggest increasing or decreasing the temperature by how many degrees, increasing or decreasing the pulling speed by how much, etc. The crystal pulling process can be adjusted in a timely and accurate manner according to these suggestions, so as to optimize the production process and improve the quality and production efficiency of the crystal.

[0074] In a possible implementation manner, the environmental information includes at least one of raw materials, auxiliary materials, thermal field, and crucible.

[0075] Among them, the raw material is the basic substance for growing crystals. For example, when preparing monocrystalline silicon, the raw material is usually high-purity polysilicon. It is melted at high temperature and crystallized under specific conditions to form the required crystal. Its purity, composition, etc. directly affect the final crystal quality and are the core component source for crystal growth.

[0076] Auxiliary materials are materials that play an auxiliary role. Although their content is relatively small, they are crucial for the process advancement and the improvement of crystal quality. For example, when pulling semiconductor crystals, dopants are added to change the conductivity type and performance of the crystal, and covering agents such as silicon dioxide are also used to prevent the raw material from reacting with the outside world or reducing heat radiation loss.

[0077] The thermal field is a system that creates a specific temperature environment and distribution state for crystal growth. It provides heat through heating elements (such as graphite heaters) to melt the raw material, and insulation materials (such as insulation felts) reduce heat dissipation to maintain temperature stability. At the same time, by precisely controlling the temperature gradient within the thermal field, the crystal is guided to grow orderly in a predetermined manner, which is a key factor to ensure the quality and efficiency of crystal pulling.

[0078] The crucible is a key container for holding raw materials to achieve crystal growth. It needs to withstand high temperatures, high pressures, and chemical erosion from the raw materials. It is usually made of specific materials. For example, high-purity quartz crucibles are commonly used in single-crystal silicon crystal pulling. With good high-temperature resistance and chemical stability, they ensure the stability of the raw material melting and crystal growth processes. However, they will gradually wear out with use.

[0079] In the crystal pulling production process, it is crucial to determine the environmental information of the current crystal pulling process. This environmental information is not a single factor but includes at least one of the raw materials (such as basic crystal growth substances like high-purity polysilicon), auxiliary materials (such as dopants, covering agents, etc., which are auxiliary materials), the thermal field (a system composed of heating elements, heat insulation materials, etc., that creates a specific temperature environment and distribution state for crystal growth), and the crucible (a container for holding raw materials to achieve crystal growth, which needs to withstand high temperatures, high pressures, and chemical erosion). By determining these key factors, it can provide a strong basis for the stable operation and quality assurance of the crystal pulling process.

[0080] In a possible implementation, multiple data such as the furnace platform data, quality data, production capacity data, process step time, and auxiliary material information of the crystal pulling process are obtained respectively. According to the time series of each data item, the furnace platform data, quality data, production capacity data, process step time, and auxiliary material information corresponding to the time are associated, and a globally unique identifier is generated for each obtained associated data. The associated data includes production parameters and environmental information.

[0081] Among them, the furnace platform data can reflect the operating status and key parameters of the crystal pulling equipment. It covers multiple aspects such as the temperature, pressure, and gas flow rate inside the furnace. The temperature data inside the furnace is one of the core indicators. It needs to be precisely controlled within a specific range at different growth stages. For example, during the polysilicon melting stage, high temperatures are required to fully melt the raw materials, while during the crystal growth stage, a stable temperature gradient needs to be maintained. Minor fluctuations in temperature may affect the crystal quality. The pressure data is also crucial. An appropriate pressure inside the furnace can ensure the smooth progress of the physical and chemical changes during the melting and crystallization of the raw materials, avoiding abnormal reactions or crystal defects. The gas flow rate data affects the atmosphere inside the furnace. The flow rates of protective gases such as nitrogen and argon need to be precisely adjusted to prevent raw material oxidation and impurity introduction. The furnace platform data reflects the operating conditions of the equipment in real time. By detecting and analyzing these data, operators can promptly discover equipment abnormalities and adjust process parameters to ensure the stable progress of the crystal pulling process.

[0082] Quality data directly reflects the quality status of the crystals produced during the crystal pulling process. It includes key indicators such as the resistivity, dislocation density, oxygen content, and carbon content of the crystals. Resistivity is an important parameter for measuring the electrical properties of semiconductor crystals. Different application scenarios have different requirements for resistivity, and the resistivity of the crystals can be adjusted by precisely controlling the crystal pulling process parameters. The dislocation density reflects the number of internal defects in the crystal. Dislocations can affect the mechanical and electrical properties of the crystal, and reducing the dislocation density is one of the key goals for improving the crystal quality. The impurity contents such as oxygen content and carbon content also need to be strictly controlled. Excessive impurities will cause the crystal performance to decline, such as reducing the carrier mobility, etc. Quality data is an important basis for evaluating the effectiveness of the crystal pulling process. By analyzing the quality data, the key factors affecting the crystal quality can be identified, and then the crystal pulling process can be optimized.

[0083] Production capacity data reflects the production efficiency and scale of the crystal pulling production line. It mainly includes indicators such as the output per furnace, production cycle, and equipment utilization rate. The output per furnace refers to the number or weight of crystals produced during each crystal pulling process. Increasing the output per furnace can increase the total output without increasing the number of equipment, and reduce the production cost. The production cycle is the total time required from the start of preparing for crystal pulling to the completion of crystal growth and removal. Shortening the production cycle can improve the turnover rate of the equipment and increase the output per unit time. The equipment utilization rate reflects the proportion of the effective operating time of the equipment in actual production. A high equipment utilization rate means that the equipment is fully utilized and the idle time is reduced. Production capacity data is crucial for the enterprise's production planning and cost control. The enterprise can reasonably arrange production tasks, optimize the production process, and improve production efficiency according to the production capacity data.

[0084] The crystal pulling process usually consists of multiple process steps, each with its specific operations and goals, and the process step time is an indicator for measuring the execution duration of each process step. For example, the process step time for loading materials includes the time for accurately placing the raw materials and auxiliary materials into the crucible and making preparations; the process step time for heating up is the time for raising the temperature in the furnace from the initial state to the temperature required for melting the raw materials; the process step time for crystal growth is the time for the crystal to grow from the start to the predetermined size; the process step time for cooling is the time for gradually cooling the crystal to a safe removal temperature after crystal growth is completed. The reasonable control of the process step time is very important for ensuring the crystal pulling quality and improving production efficiency. If the process step time of a certain step is too long, it may lead to energy waste and an extended production cycle; while if the process step time is too short, the corresponding operations may not be completed or the crystal growth quality may be affected.

[0085] The auxiliary material information includes the types, specifications, usage amounts, and usage times of various auxiliary materials used during the crystal pulling process. Although the content of auxiliary materials in the crystal is relatively small, they play an important role in the smooth progress of the crystal pulling process and the improvement of crystal quality. For example, the types and usage amounts of dopants will directly affect the conduction type and electrical properties of the crystal, and appropriate dopants need to be selected and their usage amounts precisely controlled for different application scenarios. The covering agent can prevent the raw materials from reacting with the surrounding environment and reduce heat radiation loss, and its specifications and usage time need to be selected according to the specific crystal pulling process and raw material characteristics.

[0086] In a possible implementation manner, multiple data including the furnace platform data, quality data, production capacity data, process step time, and auxiliary material information during the crystal pulling process are respectively obtained, including:

[0087] Obtain the furnace platform data from the single crystal furnace centralized control system;

[0088] Obtain the quality data and production capacity data from the production management system;

[0089] Obtain the process step time from the working hour system;

[0090] Obtain the auxiliary material information from the material system.

[0091] As the core control platform for crystal pulling production, the single crystal furnace centralized control system records and manages various parameters and status information during the operation of the single crystal furnace in real time. By extracting the data from the single crystal furnace centralized control system, the actual operation situation of the furnace platform during the crystal pulling process can be accurately grasped.

[0092] The quality data and production capacity data are sourced from the production management system. The production management system is responsible for overall quality control and production schedule arrangement of the entire production process, and details data such as the quality inspection results of crystal pulling products and the completion situation of production plans. Obtaining these data from the production management system helps to comprehensively evaluate the quality level and production efficiency of crystal pulling production.

[0093] The acquisition of process step time data depends on the working hour system. The working hour system is used to record the time consumption of each process link during crystal pulling production, accurate to the start and end times of each process step. With the help of the working hour system, the time allocation situation of each stage of crystal pulling production can be clearly understood, providing a basis for optimizing the production process and improving production efficiency.

[0094] The auxiliary material information is obtained from the material system. The material system manages all process information such as the procurement, inventory, and usage of various auxiliary materials required for crystal pulling production. Through the material system, the types, quantities, usage situations, etc. of auxiliary materials can be understood in a timely manner, ensuring the timeliness and accuracy of auxiliary material supply and guaranteeing the smooth progress of crystal pulling production.

[0095] In a possible implementation, according to user permissions, some or all of the associated data is displayed through a visual page.

[0096] In the data management and application system, in order to meet the needs of different users for data viewing and analysis, the system will accurately process the associated data based on the key factor of user permissions. Specifically, instead of presenting all the associated data to each user without discrimination, the system selectively displays the data content to users through the visual page, an intuitive and convenient display form. In this way, both the security and confidentiality of the data can be ensured, and users can efficiently obtain the information they need according to their own requirements.

[0097] User permissions are the core basis for determining the data display scope. Different users play different roles in the organizational structure and have different job responsibilities, so their data requirements and access permissions are also different. For example, grass-roots operators may only need to view some data directly related to their work tasks to complete their daily operations smoothly; while management personnel need to comprehensively understand the overall business data to make scientific and reasonable decisions. The system will accurately judge the data scope that each user can access according to the pre-set permission rules to ensure the rationality and pertinence of data display.

[0098] The visual page is an efficient data display method. It can present complex data in the form of intuitive charts, graphs, tables, etc., greatly reducing the difficulty for users to understand the data. At the same time, users can flexibly select to view some or all of the associated data on the visual page according to their own needs. This personalized data display method not only improves the efficiency of users obtaining information, but also provides strong support for users to conduct data analysis and decision-making. Displaying the associated data through the visual page realizes the effective docking of data and user needs.

[0099] In a possible implementation, in response to an operation on some of the associated data, other associated data is displayed in the visual page.

[0100] In today's data management and application scenarios, the visual page has become an important tool for people to obtain and analyze data. When users face the associated data displayed on the visual page, they often will not be satisfied with just viewing the current presented part of the content, but will, based on their own needs, perform operations on some of the data, such as clicking on a data point, selecting a specific data area, etc. Behind this operation behavior, there is often the intention of users to further explore the associated data and dig out more valuable information.

[0101] When the user operates on a part of the associated data, the system will keenly capture this interaction signal and respond quickly. The system has pre-set the association logic and display rules between data. Based on these rules, the system will accurately locate other relevant data according to the part of the data operated by the user. Subsequently, the system will dynamically display the filtered other data on the visualization page. This process is not simply a data pile-up, but is carefully calculated and filtered to ensure that the displayed data is closely related to the part of the data operated by the user, and can help the user understand the meaning behind the data more comprehensively and deeply.

[0102] This way of responding to operations and displaying other data greatly improves the user's data exploration and analysis efficiency. The user does not need to manually search for relevant information in the vast amount of data. By simply operating, the user can quickly obtain other associated data, thus broadening the data vision and discovering potential connections and rules between the data.

[0103] Figure 2 It is a schematic structural diagram of the monitoring device for the single crystal pulling process provided by this application. As Figure 2 shown, the monitoring device 200 for the single crystal pulling process provided in this embodiment includes:

[0104] A determination module 201, configured to determine the environmental information of the current single crystal pulling process;

[0105] An acquisition module 202, configured to acquire a prediction model that matches the environmental information;

[0106] The determination module 201 is further configured to input the production parameters of each process step in the current single crystal pulling process into the prediction model to obtain a prediction result output by the prediction model. The prediction result is used to indicate whether there is an abnormality and the type of abnormality in the case of an abnormality, and / or is used to indicate a production parameter adjustment strategy, where the prediction model is obtained based on the historical environmental information corresponding to the historical single crystal pulling process and the historical production parameters of each process step.

[0107] In an optional implementation manner, the determination module 201 is further configured to input the production parameters of each process step in the current single crystal pulling process into a classification model to obtain a first prediction result. The first prediction result is used to indicate whether there is an abnormality and the type of abnormality in the case of an abnormality;

[0108] The determination module 201 is further configured to input the production parameters of each process step in the current single crystal pulling process into a regression model to obtain a second prediction result. The second prediction result is used to indicate a control parameter adjustment strategy.

[0109] In an optional implementation manner, the determination module 201 is further configured to the environmental information includes at least one of raw materials, auxiliary materials, thermal field, and crucible.

[0110] In an alternative embodiment, the acquisition module 202 is further configured to acquire multiple pieces of data including the furnace platform data, quality data, production capacity data, process step time, and auxiliary material information during the crystal pulling process respectively;

[0111] The determination module 201 is further configured to correlate the furnace platform data, quality data, production capacity data, process step time, and auxiliary material information corresponding to the time according to the time series of each piece of data, and generate a globally unique identifier for each obtained correlated data. The correlated data includes production parameters and environmental information.

[0112] In an alternative embodiment, the acquisition module 202 is further configured to acquire furnace platform data from the single crystal furnace centralized control system;

[0113] The acquisition module 202 is further configured to acquire quality data and production capacity data from the production management system;

[0114] The acquisition module 202 is further configured to acquire process step time from the working hour system;

[0115] The acquisition module 202 is further configured to acquire auxiliary material information from the material system.

[0116] In an alternative embodiment, the monitoring device for the single crystal furnace crystal pulling process further includes: a processing module 203;

[0117] The processing module 203 is further configured to display some or all of the data in the correlated data through a visualization page according to the user permissions.

[0118] In an alternative embodiment, the processing module 203 is further configured to, in response to an operation on some of the data in the correlated data, display other data in the correlated data on the visualization page.

[0119] Figure 3 This is a schematic structural diagram of the monitoring device for the single crystal furnace crystal pulling process provided by the present application. As Figure 3 shown, the present application provides a monitoring device for the single crystal furnace crystal pulling process. The monitoring device 300 for the single crystal furnace crystal pulling process includes: a receiver 301, a transmitter 302, a processor 303, and a memory 304.

[0120] The receiver 301 is configured to receive instructions and data;

[0121] The transmitter 302 is configured to send instructions and data;

[0122] The memory 304 is configured to store computer execution instructions;

[0123] A processor 303 is configured to execute computer-executable instructions stored in a memory 304 to implement the respective steps performed by the monitoring method for the single crystal furnace crystal pulling process in the above embodiments. For specific details, reference can be made to the relevant descriptions in the embodiments of the monitoring method for the single crystal furnace crystal pulling process described above.

[0124] Optionally, the above-mentioned memory 304 can be either independent or integrated with the processor 303.

[0125] When the memory 304 is independently provided, the electronic device further includes a bus for connecting the memory 304 and the processor 303.

[0126] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the monitoring method for the single crystal furnace crystal pulling process performed by the above-mentioned monitoring device for the single crystal furnace crystal pulling process.

[0127] This application also provides a computer program product including a computer program, which, when executed by a processor, implements the above method.

[0128] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above method.

[0129] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk or an optical disk. The readable storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0130] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in a device.

[0131] The division of units is merely a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the couplings or direct couplings or communication connections shown or discussed among each other can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0132] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0133] In addition, in each embodiment of the present invention, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0134] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks or optical discs and other various media that can store program codes.

[0135] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the aforementioned storage medium includes: ROM, RAM, magnetic disks or optical discs and other various media that can store program codes.

[0136] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present invention, which follow the general principles of the present invention and include known common knowledge or conventional technical means in the technical field not disclosed in the present invention. It is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

Claims

1. A monitoring method for the crystal pulling process of a single crystal furnace, characterized in that, Including: Determine the environmental information of the current crystal pulling process, and obtain a prediction model that matches the environmental information; Input the production parameters of each process step in the current crystal pulling process into the prediction model, and obtain a prediction result output by the prediction model. The prediction result is used to indicate whether there is an abnormality and the type of abnormality in the case of an abnormality, and / or is used to indicate a production parameter adjustment strategy, where the prediction model is obtained based on the historical environmental information corresponding to the historical crystal pulling process and the historical production parameters of each process step.

2. The method according to claim 1, characterized in that, The prediction model includes a classification model and a regression model, and the prediction result includes a first prediction result and a second prediction result; Input the production parameters of each process step in the current crystal pulling process into the classification model to obtain a first prediction result, where the first prediction result is used to indicate whether there is an abnormality and the type of abnormality in the case of an abnormality; Input the production parameters of each process step in the current crystal pulling process into the regression model to obtain a second prediction result, where the second prediction result is used to indicate a control parameter adjustment strategy.

3. The method according to claim 1, characterized in that The environmental information includes at least one of raw materials, auxiliary materials, thermal field, and crucible.

4. The method according to any one of claims 1 to 3, characterized in that, Also included: Obtain multiple data such as furnace platform data, quality data, production capacity data, process step time, and auxiliary material information of the crystal pulling process respectively. According to the time series of each data item, associate the furnace platform data, quality data, production capacity data, process step time, and auxiliary material information corresponding to the time, and generate a globally unique identifier for each obtained associated data. The associated data includes the production parameters and the environmental information.

5. The method according to claim 4, wherein The obtaining multiple data such as furnace platform data, quality data, production capacity data, process step time, and auxiliary material information of the crystal pulling process respectively includes: Obtain the furnace platform data from the single crystal furnace centralized control system; Obtain the quality data and the production capacity data from the production management system; Obtain the process step time from the working hour system; Obtain the auxiliary material information from the material system.

6. The method according to claim 4, characterized in that Also included: Display some or all of the data in the associated data through a visualization page according to the user's permissions.

7. The method according to claim 6, wherein Also included: In response to an operation on some of the associated data, display other data in the associated data on the visualization page.

8. A monitoring device for the crystal pulling process of a single crystal furnace, characterized in that, Including: A determination module, configured to determine the current preparation stage during the preparation of single crystal silicon, where the single crystal silicon preparation process includes the following preparation stages in chronological order: preheating stage, melting stage, pulling stage, and cooling stage; The determination module is further configured to determine a monitoring algorithm and a target temperature for the crystal pulling process of the single crystal furnace corresponding to the current preparation stage; A control module, configured to control the crucible temperature according to the target temperature using the monitoring algorithm for the crystal pulling process of the single crystal furnace during the current preparation stage.

9. A monitoring device for the crystal pulling process of a single crystal furnace, characterized in that, Including: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method according to any one of claims 1 to 7.

Images