Polycrystalline silicon rod production information tracing method, device, equipment and medium

Abstract

The invention relates to a polycrystalline silicon rod production information tracing method, device, equipment and medium, and the method comprises the steps: taking the basic information of silicon powder for producing a polycrystalline silicon rod as a data field, importing the data field into a label code generation system, and generating first tracing information through the label code generation system according to the data field based on a preset query condition; determining second tracing information according to the growth information of the polycrystalline silicon rod in the production process and the growth information of the polycrystalline silicon rod generated historically under the same growth condition as the polycrystalline silicon rod; third tracing information is generated according to the event information of the polycrystalline silicon rods in the transportation and packaging line circulation process, and according to the third tracing information, popup prompt is conducted on the event information corresponding to transportation and packaging of the polycrystalline silicon rods in the inspection system; and generating and printing a production information identifier of the polycrystalline silicon rod according to the first tracing information, the second tracing information and the third tracing information of the polycrystalline silicon rod.

Description

Technical Field

[0001] The present disclosure relates to the technical field of polysilicon production, and in particular to a method, device, equipment and medium for tracing production information of polysilicon rods. Background Art

[0002] During the polysilicon production process, the quality traceability of silicon rods is usually carried out through comprehensive inspections manually from various business systems such as WMS (Warehouse Management System), MES (Manufacturing Execution System), inspection systems, and logistics video surveillance systems based on batch information after customer feedback.

[0003] First, find the quality inspection and production team of the batch, and then query the relevant monitoring information of the corresponding time according to the production time of the batch. This method is time-consuming and labor-intensive. It is very difficult to find the target scene in a large number of video resources, and it is easy to miss, make mistakes, and be chaotic. On the other hand, there is a serious disconnection with the process management of the enterprise. Summary of the invention

[0004] The purpose of the present invention is to provide a polysilicon rod production information tracing method, device, equipment and medium, aiming to solve the above problems, by combining the video monitoring of the production process, labeling the video at each key node, and making pop-up window processing for abnormal events in the product transportation and packaging line silicon rod circulation process, and when querying the video, quickly retrieve the target video according to the label information. Thereby reducing the query cost and improving the relevance of management.

[0005] In order to achieve the above-mentioned object, a first aspect of an embodiment of the present disclosure provides a method for tracing production information of polycrystalline silicon rods, the method comprising:

[0006] Importing basic information of silicon powder used to produce the polysilicon rods as a data field into a label code generation system, and generating first traceability information according to the data field through the label code generation system based on a preset query condition;

[0007] Determine second traceability information of the polycrystalline silicon rod according to growth information of the polycrystalline silicon rod during the production process and growth information of the polycrystalline silicon rod historically generated under the same growth conditions as the polycrystalline silicon rod;

[0008] According to the event information of the polycrystalline silicon rods in the process of production, transportation and packaging line circulation, third traceability information of the polycrystalline silicon rods is generated, and according to the third traceability information, event information corresponding to the transportation and packaging of the polycrystalline silicon rods is prompted in a pop-up window in the inspection system;

[0009] A production information identification of the polycrystalline silicon rod is generated and printed according to the first traceability information, the second traceability information and the third traceability information of the polycrystalline silicon rod, wherein the production information identification is used to query the production information of the polycrystalline silicon rod.

[0010] In a possible implementation, determining the second traceability information of the polycrystalline silicon rod according to the growth information of the polycrystalline silicon rod in the production process and the growth information of the polycrystalline silicon rod historically generated under the same growth conditions as the polycrystalline silicon rod includes:

[0011] Based on the growth information of the polycrystalline silicon rod during the production process and the growth information of the polycrystalline silicon rod historically generated under the same growth conditions as the polycrystalline silicon rod;

[0012] Determining whether the growth of the polycrystalline silicon rod is at a critical node according to a growth Pearson correlation coefficient between the polycrystalline silicon rod and the polycrystalline silicon rod historically generated under the same growth conditions;

[0013] If the growth of the polysilicon rod is at the critical node, a critical node label is added to the corresponding monitoring video;

[0014] The second traceability information is generated according to the production information of the polysilicon rods during the production process and the monitoring video corresponding to the key node label.

[0015] In a possible implementation, the growth information includes a growth diameter and a growth length, and the growth Pearson correlation coefficient between the growth information of the polycrystalline silicon rod during the production process and the growth information of the polycrystalline silicon rod historically generated under the same growth conditions as the polycrystalline silicon rod includes:

[0016] Discretizing the growth diameter and the growth length of the polycrystalline silicon rod during the production process according to production time points to obtain the growth diameter and the growth length corresponding to different production time points;

[0017] A first growth Pearson correlation coefficient between the growth diameters of the polycrystalline silicon rods at different production time points during the production process and the growth diameters of the polycrystalline silicon rods historically generated under the same growth conditions as the polycrystalline silicon rods;

[0018] A second growth Pearson correlation coefficient is determined based on the growth length of the polycrystalline silicon rod at different production time points during the production process and the growth length of the polycrystalline silicon rod historically generated under the same growth conditions as the polycrystalline silicon rod.

[0019] In a possible implementation, determining whether the growth of the polycrystalline silicon rod is at a critical node according to a growth Pearson correlation coefficient between the polycrystalline silicon rod and the polycrystalline silicon rod historically generated under the same growth conditions includes:

[0020] Acquire a preset first threshold set and a second threshold set, wherein the first threshold set and the second threshold set respectively include a plurality of first thresholds and a plurality of second thresholds;

[0021] Compare a first growth Pearson correlation coefficient between the polycrystalline silicon rod and the polycrystalline silicon rod historically generated under the same growth conditions with a plurality of the first thresholds in the first threshold set to obtain a first comparison result;

[0022] Compare a second growth Pearson correlation coefficient between the polycrystalline silicon rod and the polycrystalline silicon rod historically generated under the same growth conditions with a plurality of the second thresholds in the second threshold set to obtain a second comparison result;

[0023] Whether the growth of the polycrystalline silicon rod is at a critical node is determined according to the first comparison result and the second comparison result.

[0024] In a possible implementation, the generating of the third traceability information of the polycrystalline silicon rod according to the event information of the polycrystalline silicon rod in the process of production, transportation and packaging line circulation includes:

[0025] Generate production events according to event information of the polycrystalline silicon rods during production, transportation and packaging line circulation;

[0026] Determining whether the production event of the polycrystalline silicon rod is an abnormal event;

[0027] If the production event of the polycrystalline silicon rod is an abnormal event, an abnormal label is marked on the monitoring video of the polycrystalline silicon rod during the production, transportation and packaging process;

[0028] The third traceability information of the polycrystalline silicon rod is generated according to the abnormal label of the polycrystalline silicon rod and the monitoring video marked with the abnormal label.

[0029] In a possible implementation manner, the determining whether the production event of the polycrystalline silicon rod is an abnormal event includes:

[0030] According to the temperature in the reduction furnace, the concentration of the feed gas, the material flow rate and the impurity content of the polycrystalline silicon rods in the previous process, a historical operation curve model is configured to predict the predicted impurity content of the polycrystalline silicon rods in the subsequent process;

[0031] Determining whether the impurity content of the polycrystalline silicon rod is abnormal in each of the processes according to the predicted impurity content of each of the processes and the corresponding impurity content threshold value set for each of the processes;

[0032] The real-time images, historical personnel operation records, quality information retrieval records and equipment status monitoring information of the polycrystalline silicon rods during the transportation and packaging line flow are stored in an event information database;

[0033] Identify the real-time images, historical personnel operation records, quality information retrieval records and equipment status monitoring information to determine whether there are any information anomalies;

[0034] Whether the production event of the polycrystalline silicon rod is an abnormal event is determined according to the first result of whether the impurity content of the polycrystalline silicon rod is abnormal in each of the processes and the second result of whether the information is abnormal.

[0035] In a possible implementation, the historical operation curve model is trained in the following manner:

[0036] Construct a regression equation: I = β0 + β1T + β2C + β3*F + ε, wherein I is the impurity content, T is the temperature in the reduction furnace, C is the concentration of the feed gas, F is the material flow rate of the polysilicon rod in the previous process, β0 is the intercept term, β1, β2, β3 are regression coefficients, and ε is the error term;

[0037] According to the temperature in the reduction furnace corresponding to the polycrystalline silicon rods produced historically, the concentration of the feed gas, the material flow rate and the impurity content of the polycrystalline silicon rods in the previous process, the least squares method is used to estimate the intercept term β0, the regression coefficient β1, the regression coefficient β2 and the regression coefficient β3 of the regression equation;

[0038] When the intercept term β0, the regression coefficient β1, the regression coefficient β2 and the regression coefficient β3 of the regression equation are determined, the model parameters are adjusted through cross-validation to obtain the historical operation curve model.

[0039] According to a second aspect of the embodiments of the present disclosure, there is provided a polycrystalline silicon rod production information tracing device, the device comprising:

[0040] A first generating module is configured to import basic information of silicon powder used to produce the polycrystalline silicon rod as a data field into a label code generating system, and based on a preset query condition, generate first traceability information according to the data field through the label code generating system;

[0041] A second generating module is configured to determine second traceability information of the polycrystalline silicon rod according to growth information of the polycrystalline silicon rod in the production process and growth information of the polycrystalline silicon rod historically generated under the same growth conditions as the polycrystalline silicon rod;

[0042] A third generating module is configured to generate third traceability information of the polycrystalline silicon rod according to event information of the polycrystalline silicon rod in the process of transportation and packaging line circulation, and to pop up a window prompt in the inspection system for event information corresponding to the transportation and packaging of the polycrystalline silicon rod according to the third traceability information;

[0043] The fourth generation module is configured to generate and print the production information identification of the polycrystalline silicon rod according to the first traceability information, the second traceability information and the third traceability information of the polycrystalline silicon rod, wherein the production information identification is used to query the production information of the polycrystalline silicon rod.

[0044] According to a third aspect of the present disclosure, an electronic device is provided, including:

[0045] a memory having a computer program stored thereon;

[0046] A processor is used to execute the computer program in the memory to implement the steps of any one of the methods in the first aspect.

[0047] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the steps of any one of the methods described in the first aspect are implemented.

[0048] The present invention provides a method, device, equipment and medium for tracing the production information of polysilicon rods. Compared with the prior art, it has the following beneficial effects:

[0049] By integrating the basic information of silicon powder, the growth information of silicon rods, and the event information during production, transportation and packaging, this method can fully cover the entire chain of polysilicon rod production and ensure the integrity and accuracy of the information. The label code generation system is used to generate the first traceability information, and the second traceability information is determined based on the growth information and historical data. The third traceability information is then generated in combination with the event information during the production flow process, and finally the production information label is generated and printed, which enhances the convenience of information traceability.

[0050] It not only records the basic information and growth process of polysilicon rods, but also records in detail every important event in the production, transportation and packaging process. This helps enterprises to achieve refined production management and timely discover and solve problems. It improves the refinement of production management. By comparing the growth information of current silicon rods with historical silicon rods, abnormalities in the production process can be discovered in time, thereby strengthening quality control. At the same time, pop-up window prompts for event information during transportation and packaging help enterprises to promptly discover and respond to potential risks, and promote information and intelligent production.

[0051] In summary, the digitalization, networking and intelligent management of polysilicon rod production information has been realized. This helps enterprises improve production efficiency, reduce costs and enhance market competitiveness. Through comprehensive, convenient and detailed information tracing methods, the level and quality of polysilicon rod production management have been effectively improved, and the information and intelligent production of enterprises have been promoted.

[0052] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0054] Figure 1 It is a flow chart of a method for tracing production information of polysilicon rods according to an embodiment of the specification.

[0055] Figure 2 It is a block diagram of a polysilicon rod production information tracing device according to an embodiment of the specification.

[0056] Figure 3 It is a block diagram of another polysilicon rod production information tracing device shown in an embodiment of the specification. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0059] The present invention provides a method for tracing production information of polycrystalline silicon rods. Figure 1 The present invention is a flow chart of a method for tracing polysilicon rod production information according to an embodiment. Specifically, the method includes:

[0060] In step S11, basic information of silicon powder used to produce the polycrystalline silicon rod is imported into a label code generation system as a data field, and based on a preset query condition, the label code generation system generates first traceability information according to the data field;

[0061] Among them, polycrystalline silicon rods are columnar silicon materials generated by the reaction of high-purity silicon powder at high temperature, such as polycrystalline silicon rods used in solar cells, semiconductors, etc. The label code generation system is a computer system that can generate a unique or specific rule label code (such as a barcode, QR code, etc.) based on the input data field (such as the basic information of silicon powder).

[0062] In the disclosed embodiment, the basic information of silicon powder (such as batch number, purity, source, etc.) is imported into the label code generation system as a data field. The system generates a label code corresponding to the silicon powder information one by one according to the pre-set query conditions (such as batch number, production date, etc.) and coding rules as the first traceability information. The source, batch, quality and other information of the silicon powder are recorded to ensure the traceability of the raw materials. Through the unique identification of the raw materials, the relevant information can be quickly queried to provide reliable raw material guarantee for the production process.

[0063] For example, suppose there is a batch of silicon powder with batch number 20230101 and purity of 99.999%, which comes from a silicon material supplier. After importing this information into the label code generation system, the system generates a unique QR code label, which contains basic information such as the batch number, purity, and source of the silicon powder, which is convenient for subsequent traceability.

[0064] In step S12, second traceability information of the polycrystalline silicon rod is determined according to growth information of the polycrystalline silicon rod during the production process and growth information of the polycrystalline silicon rod historically generated under the same growth conditions as the polycrystalline silicon rod;

[0065] The growth information may include key parameters such as temperature, pressure, gas flow rate, and growth cycle during the production of polycrystalline silicon rods in a growth furnace.

[0066] In the disclosed embodiment, data analysis and comparison are performed based on the growth information (such as temperature, pressure, gas flow, etc.) of the polysilicon rod during the production process and the growth information of the silicon rod historically generated under the same growth conditions as the silicon rod to determine the growth status and quality characteristics of the current silicon rod as the second traceability information.

[0067] For example: During the growth of silicon rods, the system will record the temperature, pressure and other parameters in the growth furnace in real time. At the same time, the system will retrieve the growth information of silicon rods under the same growth conditions in the historical data for comparison and analysis. If it is found that the growth parameters of the current silicon rods are significantly different from the historical data, the system will issue an early warning to prompt the operator to make adjustments.

[0068] In step S13, third traceability information of the polycrystalline silicon rod is generated according to event information of the polycrystalline silicon rod in the process of production, transportation and packaging line circulation, and event information corresponding to the transportation and packaging of the polycrystalline silicon rod is popped up in the inspection system according to the third traceability information;

[0069] Among them, the inspection system is a computer system used to monitor and check the operating status of production lines or equipment, and to promptly detect and handle abnormalities.

[0070] In the disclosed embodiment, during the production, transportation and packaging line circulation process, the system will record every important event experienced by the silicon rod (such as warehousing, outbound, transportation, packaging, etc.) and generate corresponding event information. This information is used as the third traceability information to track the circulation process of the silicon rod. At the same time, the system will pop up a window prompt for the event information corresponding to the transportation and packaging of the silicon rod in the inspection system based on the third traceability information to ensure that the operator can promptly discover and handle abnormal situations.

[0071] For example: When the silicon rod is taken out of the growth furnace, the system will record its storage time and storage location information. When the silicon rod needs to be transported to the packaging line, the system will record information such as transportation time, transportation method and transportation personnel. During the packaging process, the system will record information such as packaging time, packaging materials and packaging personnel. If an abnormality occurs in a certain link (such as packaging materials that do not meet the requirements), the system will pop up a prompt window in the inspection system to remind the operator to deal with it in time.

[0072] In step S14, a production information identification of the polycrystalline silicon rod is generated and printed according to the first traceability information, the second traceability information and the third traceability information of the polycrystalline silicon rod, wherein the production information identification is used to query the production information of the polycrystalline silicon rod.

[0073] Among them, the production information identification is able to track and record information from raw materials to finished products, including raw material information, production process information, transportation information, quality inspection information, etc.

[0074] In the disclosed embodiment, the first traceability information, the second traceability information and the third traceability information are integrated and processed to generate a production information label containing all the production information of the silicon rod. The label can be in the form of a barcode, a QR code, etc., to facilitate subsequent query and tracing. Then, the system will print out the production information label and attach it to the silicon rod or deliver it to the customer together with its packaging.

[0075] For example: After completing the first three steps, the system will generate a production information label containing basic information of silicon powder, growth information, circulation event information, etc. The label is presented in the form of a QR code and printed on the packaging of the silicon rod. Customers or subsequent users can quickly obtain all the production information of the silicon rod by scanning the QR code.

[0076] The above technical solution integrates the basic information of silicon powder, the growth information of silicon rods, and the event information during production, transportation and packaging. This method can fully cover the entire chain of polysilicon rod production and ensure the integrity and accuracy of the information. The label code generation system is used to generate the first traceability information, and the second traceability information is determined based on the growth information and historical data. The third traceability information is generated in combination with the event information during the production flow process, and finally the production information label is generated and printed, which enhances the convenience of information traceability.

[0077] It not only records the basic information and growth process of polysilicon rods, but also records in detail every important event in the production, transportation and packaging process. This helps enterprises to achieve refined production management and timely discover and solve problems. It improves the refinement of production management. By comparing the growth information of current silicon rods with historical silicon rods, abnormalities in the production process can be discovered in time, thereby strengthening quality control. At the same time, pop-up window prompts for event information during transportation and packaging help enterprises to promptly discover and respond to potential risks, and promote information and intelligent production.

[0078] In summary, the digitalization, networking and intelligent management of polysilicon rod production information has been realized. This helps enterprises improve production efficiency, reduce costs and enhance market competitiveness. Through comprehensive, convenient and detailed information tracing methods, the level and quality of polysilicon rod production management have been effectively improved, and the information and intelligent production of enterprises have been promoted.

[0079] In a possible implementation, in step S12, determining the second traceability information of the polycrystalline silicon rod according to the growth information of the polycrystalline silicon rod in the production process and the growth information of the polycrystalline silicon rod historically generated under the same growth conditions as the polycrystalline silicon rod includes:

[0080] In step S121, according to the growth information of the polycrystalline silicon rod in the production process and the growth information of the polycrystalline silicon rod historically generated under the same growth conditions as the polycrystalline silicon rod, the growth Pearson correlation coefficient is calculated;

[0081] Among them, the Pearson correlation coefficient is a statistic that measures the degree of linear correlation between two variables, and its value range is between -1 and 1. In the context of polysilicon rod production, the growth Pearson correlation coefficient is used to measure the linear correlation between the growth information of the current silicon rod and the growth information of the silicon rod under the same historical conditions. A high correlation coefficient indicates that the growth trends of the two are similar, while a low correlation coefficient may mean that the growth of the current silicon rod is abnormal.

[0082] In the disclosed embodiment, the Pearson correlation coefficient formula in statistics is used to calculate the correlation coefficient between the current growth information of the polysilicon rod (such as temperature, pressure, gas flow rate, etc.) and the growth information of the silicon rod under the same historical conditions. The calculation of the correlation coefficient is based on the covariance and standard deviation of the two sets of data, reflecting the strength of the linear relationship between the two.

[0083] For example: Assume that the current silicon rod growth temperature is T1, pressure is P1, and gas flow is F1; while the silicon rod growth temperature under the same conditions in the past is T2, pressure is P2, and gas flow is F2. By calculating the Pearson correlation coefficient between these two sets of data, it is possible to evaluate whether the current silicon rod growth trend is consistent with the historical data.

[0084] In step S122, determining whether the growth of the polycrystalline silicon rod is at a critical node based on the growth Pearson correlation coefficient between the polycrystalline silicon rod and the polycrystalline silicon rod historically generated under the same growth conditions;

[0085] Among them, key nodes are production stages or time points in the production process of polysilicon ingots that have a significant impact on the quality, performance or production efficiency of the ingots. These nodes are usually related to significant changes in growth parameters, potential quality problems or key operations in the production process.

[0086] In the disclosed embodiment, a threshold is set based on the calculated growth Pearson correlation coefficient to determine whether the current silicon rod growth is at a critical node. If the correlation coefficient is lower than the threshold, it indicates that the current silicon rod growth trend is significantly different from the historical data and may be at a critical node.

[0087] For example: if the threshold is set to 0.8, and the calculated growth Pearson correlation coefficient between the current silicon rod and the historical silicon rod is 0.6, which is lower than the threshold, it is judged that the growth of the current silicon rod is at a critical node.

[0088] In step S123, if the growth of the polysilicon rod is at the critical node, a critical node label is added to the corresponding monitoring video;

[0089] Among them, surveillance video key node tags are usually marked in the production process to record and analyze the detailed information of key nodes. These tags are called key node tags, which are used to indicate specific time periods or frames in the video that contain the information of key nodes.

[0090] In the disclosed embodiment, during the production process, the monitoring system will continuously record the growth of the silicon rod. When it is determined that the silicon rod is at a critical node, the system will automatically or manually tag the corresponding monitoring video with a critical node for subsequent analysis and tracing.

[0091] For example: When the system determines that the current growth of the silicon rod is at a critical node, it will automatically find the time period corresponding to the node in the monitoring video and add critical node labels before and after the time period, such as "critical node_start" and "critical node_end".

[0092] In step S124, second traceability information is generated according to the production information of the polysilicon rods during the production process and the monitoring video corresponding to the key node label.

[0093] In the disclosed embodiment, the second traceability information is generated by combining the production information (such as batch number, growth time, growth parameters, etc.) of the current silicon rod in the production process and the monitoring video corresponding to the key node label. This information is used to record in detail the key stages and abnormal conditions of the silicon rod in the growth process.

[0094] For example, suppose the current silicon rod batch number is 20230401, the growth time is from April 1 to April 5, and it is at a critical node on April 3. Then, the second traceability information will include the batch number, growth time, the critical node label on April 3, and the corresponding monitoring video link or summary. This information will be integrated into the production information identification for subsequent query and traceability.

[0095] The above technical solution can accurately identify whether the current growth state of silicon rods is significantly different from historical data by calculating the Pearson correlation coefficient of the growth of silicon rods under the same conditions in the past. Such a difference may indicate potential growth anomalies or quality problems, providing a basis for taking corrective measures in a timely manner.

[0096] Based on the comparison of the growth Pearson correlation coefficient with the preset threshold, the technology can intelligently locate the key nodes in the silicon rod growth process. These nodes are usually related to significant changes in growth parameters, potential quality problems or key operations in the production process, and are the focus of monitoring and traceability. The key nodes can be intelligently located.

[0097] For silicon rods at critical nodes, the technology can automatically tag the corresponding surveillance videos with critical nodes. This not only facilitates subsequent video retrieval and analysis, but also improves the management efficiency of surveillance videos. Combining the production information of silicon rods during the production process and the surveillance videos corresponding to the critical node tags, the technology can comprehensively generate the second traceability information. This information records in detail the key stages and abnormal conditions of the silicon rods during their growth process, providing strong data support for product quality traceability and problem analysis.

[0098] In summary, by introducing innovative means such as the growth Pearson correlation coefficient and key node labels, the refined monitoring and traceability of the polysilicon rod production process has been achieved. This not only improves production efficiency and quality level, but also provides strong technical support for the company's continuous improvement and intelligent production.

[0099] In a possible implementation, the growth information includes growth diameter and growth length, wherein the growth diameter refers to the cross-sectional diameter of the silicon rod at a certain growth time point during the production process of the polysilicon silicon rod. It is one of the important indicators for measuring the growth speed and morphology of the silicon rod. The growth length refers to the total length of the silicon rod from the beginning of growth to a certain growth time point. It reflects the growth progress and efficiency of the silicon rod.

[0100] In step S121, the growth Pearson correlation coefficient between the growth information of the polycrystalline silicon rod in the production process and the growth information of the polycrystalline silicon rod historically generated under the same growth conditions as the polycrystalline silicon rod includes:

[0101] In step S1211, the growth diameter and the growth length of the polycrystalline silicon rod during the production process are discretized according to the production time points to obtain the growth diameter and the growth length corresponding to different production time points;

[0102] Discretization refers to the process of dividing a continuous data set into several discrete intervals or points. In the present technical content, discretization is used to divide the growth diameter and growth length of polysilicon rods according to production time points for subsequent correlation coefficient calculation.

[0103] In the disclosed embodiment, in order to calculate the growth Pearson correlation coefficient, it is first necessary to discretize the growth diameter and growth length of the polysilicon rod during the production process according to the production time points. This means that the continuous growth process is divided into several discrete time points, and the corresponding growth diameter and growth length are recorded for each time point.

[0104] For example: Assume that the production process of polysilicon rods lasts for a week, and the growth diameter and growth length are recorded once a day. Then, the production process of this week can be discretized into 7 time points (i.e. 7 days), and the corresponding growth diameter and growth length are recorded for each time point.

[0105] In step S1212, a first growth Pearson correlation coefficient is calculated based on the growth diameters of the polycrystalline silicon rods at different production time points during the production process and the growth diameters of the polycrystalline silicon rods historically generated under the same growth conditions as the polycrystalline silicon rods;

[0106] In the disclosed embodiment, the first growth Pearson correlation coefficient is used to measure the linear correlation between the growth diameter of the current silicon rod at different production time points and the growth diameter of the silicon rod under the same historical conditions. By calculating the correlation coefficient between the two sets of data, it can be evaluated whether the growth diameter of the current silicon rod is consistent with the historical data or has a significant difference.

[0107] For example: Assume that the current silicon rod growth diameter on the first day is D1, the growth diameter on the second day is D2, ..., and the growth diameter on the seventh day is D7; and under the same historical conditions, the growth diameter of the silicon rod on the first day is D1_hist, the growth diameter on the second day is D2_hist, ..., and the growth diameter on the seventh day is D7_hist. Then, the Pearson correlation coefficient between these two sets of data can be calculated to evaluate whether the current silicon rod growth diameter is consistent with the historical data.

[0108] In step S1213, a second growth Pearson correlation coefficient is determined based on the growth lengths of the polycrystalline silicon rods at different production time points during the production process and the growth lengths of the polycrystalline silicon rods historically generated under the same growth conditions as the polycrystalline silicon rods.

[0109] In the disclosed embodiment, similar to the first growth Pearson correlation coefficient, the second growth Pearson correlation coefficient is used to measure the linear correlation between the growth length of the current silicon rod at different production time points and the growth length of the silicon rod under the same historical conditions. By calculating the correlation coefficient between the two sets of data, it can be evaluated whether the growth length of the current silicon rod is consistent with the historical data or has a significant difference.

[0110] For example: Assume that the current silicon rod growth length on the first day is L1, the growth length on the second day is L2, ..., and the growth length on the seventh day is L7; and under the same conditions in the past, the growth length of the silicon rod on the first day is L1_hist, the growth length on the second day is L2_hist, ..., and the growth length on the seventh day is L7_hist. Then, the Pearson correlation coefficient between these two sets of data can be calculated to evaluate whether the current silicon rod growth length is consistent with the historical data.

[0111] In other words, the growth Pearson correlation coefficient between the polycrystalline silicon rod and the polycrystalline silicon rod generated historically under the same growth conditions includes the first growth Pearson correlation coefficient and the second growth Pearson correlation coefficient. In this way, by calculating the first growth Pearson correlation coefficient and the second growth Pearson correlation coefficient, it is possible to comprehensively evaluate whether the growth state of the current silicon rod is consistent with the historical data, thereby providing strong data support for the subsequent key node determination and traceability information generation.

[0112] In a possible implementation, in step S122, determining whether the growth of the polycrystalline silicon rod is at a critical node according to the growth Pearson correlation coefficient between the polycrystalline silicon rod and the polycrystalline silicon rod historically generated under the same growth conditions includes:

[0113] In step S1221, a preset first threshold set and a second threshold set are obtained, wherein the first threshold set and the second threshold set respectively include a plurality of first thresholds and a plurality of second thresholds;

[0114] The threshold set is a set of multiple correlation coefficient thresholds. These thresholds are used to determine the similarity between the current growth status of the silicon rod and the historical data. Usually, these thresholds are set based on actual production experience and needs to ensure that key nodes can be accurately identified.

[0115] In step S1222, a first growth Pearson correlation coefficient between the polycrystalline silicon rod and the polycrystalline silicon rod historically generated under the same growth conditions is compared with a plurality of the first thresholds in the first threshold set to obtain a first comparison result;

[0116] In the disclosed embodiment, the calculated first growth Pearson correlation coefficient (i.e., the correlation coefficient between the growth diameter of the current silicon rod at different production time points and the historical data) is compared with the set thresholds. If the correlation coefficient is lower than a certain threshold, this may mean that the growth diameter of the current silicon rod is relatively rare or abnormal in the historical data, and therefore may be at a critical node.

[0117] In step S1223, a second growth Pearson correlation coefficient between the polycrystalline silicon rod and the polycrystalline silicon rod historically generated under the same growth conditions is compared with a plurality of the second thresholds in the second threshold set to obtain a second comparison result;

[0118] Similarly, the second growth Pearson correlation coefficient (i.e., the correlation coefficient between the growth length of the current silicon rod at different production time points and the historical data) is compared with the set threshold. If the correlation coefficient is also lower than a certain threshold, this may further confirm that the growth state of the current silicon rod is abnormal, thereby increasing the possibility that it is at a critical node.

[0119] In step S1224, it is determined whether the growth of the polycrystalline silicon rod is at a critical node based on the first comparison result and the second comparison result.

[0120] In the disclosed embodiment, after comparing the first growth Pearson correlation coefficient and the second growth Pearson correlation coefficient with the threshold, a comprehensive judgment is made. If both correlation coefficients are lower than the threshold, or one of the correlation coefficients is significantly lower than the threshold and the other also shows a certain abnormality (such as close to the threshold but lower than the historical average), then it can be considered that the current growth of the silicon rod is at a critical node.

[0121] In a possible implementation, in step S13, generating third traceability information of the polycrystalline silicon rod according to event information of the polycrystalline silicon rod in the process of production, transportation and packaging line circulation includes:

[0122] In step S131, a production event is generated according to event information of the polycrystalline silicon rods during the production, transportation and packaging line circulation process;

[0123] In the disclosed embodiment, according to preset rules and algorithms, key production events are extracted from the event information collected during the production, transportation and packaging of polysilicon rods. These event information may come from multiple data sources such as sensors, surveillance cameras, RFID tags, etc. The system will integrate and analyze this information to generate a series of event records related to the production process.

[0124] For example: During the production process, the system may record events such as the start of silicon rod growth, the end of growth, the cooling stage, and the transportation to the next process. During transportation, the system may record the transfer time of silicon rods from the production line to the warehouse, the information of the transportation vehicle, etc. During the circulation of the packaging line, the system may record events such as silicon rods being packaged, labeled, and put into storage.

[0125] In step S132, determining whether the production event of the polycrystalline silicon rod is an abnormal event;

[0126] In the embodiment of the present disclosure, the generated production events are screened and judged according to the preset abnormal event definition and judgment criteria to determine which events are abnormal events. These abnormal events may include equipment failures in the production process, deviations from the standard of process parameters, damage or contamination of silicon rods, etc.

[0127] For example, if the system finds in the monitoring data that the growth rate of the silicon rods suddenly slows down or stops, or obvious cracks or stains appear on the surface of the silicon rods, these may be regarded as abnormal events.

[0128] In step S133, if the production event of the polycrystalline silicon rod is an abnormal event, an abnormal label is added to the monitoring video of the polycrystalline silicon rod during the production, transportation and packaging process;

[0129] In the disclosed embodiment, once an abnormal event is identified, the system will automatically retrieve and mark the surveillance videos related to the abnormal event based on the time and location information of the abnormal event. These videos will be marked with abnormal tags for subsequent analysis and tracing.

[0130] For example: For example, if the system detects an abnormal event of cracks on the surface of the silicon rod during the growth process, the system will automatically find and record the surveillance videos before and after the cracks appear, and label these videos as "crack abnormality".

[0131] In step S134, third traceability information of the polycrystalline silicon rod is generated according to the abnormal label of the polycrystalline silicon rod and the monitoring video marked with the abnormal label.

[0132] Among them, the third traceability information is in the process of production, transportation and packaging of polysilicon rods. The third traceability information refers to the comprehensive data that records in detail the events (especially abnormal events) that occurred at each stage of the silicon rods and their related monitoring video information. It is used to trace the specific conditions of the silicon rods during production, transportation and packaging to ensure product quality and process compliance.

[0133] In the disclosed embodiment, third traceability information of polysilicon rods is generated based on the abnormal labels and the labeled surveillance videos. Such information will include the description of the abnormal event, the time of occurrence, the location, the link or storage location of the related surveillance video, etc. Such information will be integrated into a unified traceability system for subsequent quality control and process optimization.

[0134] For example, for a certain polysilicon rod, its third traceability information may include: during the production process, an abnormal event was detected in which cracks were found on the surface of the rod at the end of the third day of growth; the abnormal event occurred in area B of the growth workshop; the surveillance video related to the abnormal event has been labeled "crack abnormality" and stored in a specific location on the server. This information will help relevant personnel quickly locate the cause of the problem, take corrective measures, and prevent similar problems from happening again.

[0135] In a possible implementation, in step S132, determining whether the production event of the polycrystalline silicon rod is an abnormal event includes:

[0136] In step S1321, according to the temperature in the reduction furnace, the concentration of the feed gas, the material flow rate and the impurity content of the polycrystalline silicon rods in the previous process, a historical operation curve model is configured to predict the impurity content of the polycrystalline silicon rods in the later process;

[0137] Among them, the reduction furnace is a device used to convert silicon raw materials (such as trichlorosilane) into polysilicon through chemical reactions (such as thermal reduction) at high temperatures during the production of polysilicon. Feed gas is the gas input into the reduction furnace to participate in the chemical reaction, such as hydrogen, trichlorosilane, etc. Material flow rate is the amount of material passing through a certain section per unit time during the production process. Here it specifically refers to the flow rate of silicon raw materials in the front stage of polysilicon production. Impurity content is the content of other components in the material except the main component. For polysilicon, impurities may include metal elements, non-metallic elements or compounds, etc., and their content directly affects the purity of polysilicon. The historical operation curve model is a mathematical model built based on historical data to predict the future state of a system or process. Here it refers to a model used to predict the impurity content in the back-end process of polysilicon rods.

[0138] In the disclosed embodiment, historical data (including reduction furnace temperature, feed gas concentration, material flow rate and impurity content of the front-end process, etc.) are used to train a machine learning model or a statistical model to form a historical operation curve model. The model can predict the impurity content of polysilicon rods in the back-end process based on current production conditions.

[0139] For example, if historical data shows that when the reduction furnace temperature is 1200°C, the concentration of trichlorosilane in the feed gas is 95%, the material flow rate of the front-end process is 100kg / h, and the impurity content is less than 0.01%, the impurity content of the back-end process is usually less than 0.005%. Based on these data, the model can predict the impurity content of the back-end process under current conditions.

[0140] In step S1322, according to the predicted impurity content of each process and the corresponding impurity content threshold set for each process, it is determined whether the polycrystalline silicon rod has abnormal impurity content in each process;

[0141] In the disclosed embodiment, the predicted impurity content is compared with the impurity content threshold set for each process to determine whether the impurity content exceeds the acceptable range. For example, if the impurity content threshold of a process is 0.008%, and the predicted impurity content is 0.012%, then the impurity content of the process is judged to be abnormal.

[0142] In step S1323, the real-time images, historical personnel operation records, quality information retrieval records and equipment status monitoring information of the polycrystalline silicon rods during the transportation and packaging line circulation process are stored in the event information database;

[0143] The event information database is a database system that stores various data related to production events (such as real-time images, operation records, quality information, etc.). It can communicate with business systems such as WMS, MES, LIMS, packaging lines, and inspections.

[0144] In the disclosed embodiment, during the production process, real-time images of polysilicon rods during transportation and packaging line circulation, personnel operation records, quality information retrieval records and equipment status monitoring information are collected and recorded in real time, and stored in the event information database. For example: all transportation processes of silicon rods from the production line to the packaging area are recorded, including timestamps, operators, equipment status (such as whether it is operating normally), quality inspection results, etc., and stored in the database.

[0145] In step S1324, the real-time image, historical personnel operation records, quality information retrieval records and equipment status monitoring information are identified to determine whether there is any information anomaly;

[0146] In the disclosed embodiments, data analysis techniques (such as anomaly detection algorithms) are used to identify the stored information to find out whether there are abnormal patterns or behaviors, such as abnormally high error rates, non-standard operations, equipment failures, etc. For example: if data analysis finds that the equipment failure rate suddenly increases within a certain period of time, or that operators frequently perform non-standard operations, then it is determined that there is an information anomaly.

[0147] In step S1325, it is determined whether the production event of the polycrystalline silicon rod is an abnormal event based on the first result of whether the impurity content of the polycrystalline silicon rod is abnormal in each of the processes and the second result of whether the information is abnormal.

[0148] In the embodiment of the present disclosure, if the impurity content of the polysilicon rod is abnormal in a certain process, or there is abnormal information, the production event is determined to be an abnormal event. For example: if the predicted impurity content exceeds the threshold in a certain process, and at the same time it is found that the equipment status monitoring information during the period shows that the equipment has abnormal fluctuations, then the production event is determined to be an abnormal event, and further inspection and corresponding measures are required.

[0149] In a possible implementation, the historical operation curve model is trained in the following manner:

[0150] Construct a regression equation: I = β0 + β1T + β2C + β3*F + ε, wherein I is the impurity content, T is the temperature in the reduction furnace, C is the concentration of the feed gas, F is the material flow rate of the polysilicon rod in the previous process, β0 is the intercept term, β1, β2, β3 are regression coefficients, and ε is the error term;

[0151] Among them, I is the dependent variable (impurity content of polysilicon rods), T is one of the independent variables (temperature in the reduction furnace), C is the second independent variable (concentration of feed gas), and F is the third independent variable (material flow rate of polysilicon rods in the previous process).

[0152] According to the temperature in the reduction furnace corresponding to the polycrystalline silicon rods produced historically, the concentration of the feed gas, the material flow rate and the impurity content of the polycrystalline silicon rods in the previous process, the least squares method is used to estimate the intercept term β0, the regression coefficient β1, the regression coefficient β2 and the regression coefficient β3 of the regression equation;

[0153] Here, a design matrix X is constructed, where each row corresponds to a data point and each column corresponds to an independent variable (including the constant 1 for the intercept term).

[0154] Using the least squares formula, the regression coefficient β = [β0, β1, β2, β3] can be calculated by the following formula: β = (X T ×X) -1 ×X T ×Y, where Y is the vector form of the dependent variable I.

[0155] When the intercept term β0, the regression coefficient β1, the regression coefficient β2 and the regression coefficient β3 of the regression equation are determined, the model parameters are adjusted through cross-validation to obtain the historical operation curve model.

[0156] In the disclosed embodiment, after the regression coefficient is obtained, the remaining data points or a cross-validation method may be used to verify the accuracy of the model.

[0157] In the disclosed embodiment, the data set is randomly divided into k parts, and for each part, the remaining k-1 parts are used as training sets to fit the regression model, and the current fold is used as a validation set to evaluate the performance of the model. This involves calculating the error (such as mean square error MSE) between the predicted value and the actual value.

[0158] Based on the results of the cross-validation, the parameters of the regression model can be adjusted (although in this specific case we are mainly concerned with the coefficients obtained using the least squares method, cross-validation can be used to evaluate the effect of different model structures or preprocessing steps).

[0159] After cross-validation is completed, the model with the best performance on all folds is usually selected as the final model. However, in regression problems, since we have already used the least squares method to obtain the optimal solution for the coefficients (given the data and model structure), cross-validation is more used to evaluate the stability and generalization ability of the model rather than directly adjusting the coefficients.

[0160] Finally, by combining the regression coefficients obtained by the least squares method and the evaluation results of cross-validation, we can obtain a historical operating curve model that can predict the impurity content of polysilicon rods based on given temperature, concentration and flow rate. This model can be used to guide future production decisions to optimize product quality and production costs.

[0161] To achieve the above-mentioned purpose, the present invention adopts:

[0162] 1. Data collection and integration: Establish a powerful data collection platform, covering all aspects of data such as process, equipment, safety, energy, and operation. The equipment collects various data in the production process in real time, connects the data of MES, WMS, inspection, and video surveillance, and recommends a unified data platform.

[0163] 2. Traceability system model construction: Based on the production model, the process of silicon powder input, reduction furnace loading, furnace unloading, silicon rod transportation, crushing and packaging, warehousing and logistics transportation is fully monitored. Silicon powder, silicon rods, and video surveillance recordings are marked with QR codes or RFID tags. Through data analysis, the overall situation of the polysilicon production process can be grasped. For abnormal situations, the model can be combined to analyze and give reasons and treatment measures.

[0164] 3. Visual traceability system:

[0165] Raw material traceability: uniquely encode the raw materials, record the batch, source, quality and other information of the raw materials, and realize the traceability of the raw materials. Production process traceability: set up data collection points in each production link, record process parameters, equipment status, operators and other information, and associate them with the production model to realize visual traceability of the production process. Finished product traceability: uniquely encode the finished product and associate it with various data in the production process to realize the full traceability of the finished product from raw materials to finished products. Video surveillance traceability: through the video watermark OSD overlay and slice video backup function, the key information such as traceability order number, workstation name, scene name, etc. is superimposed on the video, and the forensic information is richer.

[0166] 4. Intelligent analysis and early warning: The system has built-in multiple abnormal analysis models, which can trace and analyze abnormal situations in the production process, and provide operational adjustment suggestions in combination with the expert database and knowledge base. At the same time, using online analytical instruments and LIMS historical impurity content curves, an impurity early warning model is provided. According to the material flow and impurity content of the previous process, the impurity content of the subsequent process is predicted, so as to achieve early warning and control. The threshold configuration range is synchronized with the video platform, and real-time reminders are given through video images. By analyzing the equipment operation status data, the occurrence of equipment failures can be predicted, and maintenance or replacement can be carried out in advance. The intelligent analysis and early warning module is associated with other production management modules (production planning, inventory management, quality management, energy consumption management), combined with the early warning thresholds of key parameters set by the production management system, the data is analyzed, and the analysis results are fed back to the production management system, which can achieve optimized control of inventory, quality, and energy consumption.

[0167] 5. Mobile terminals and Internet of Things technology: Combine QR code, RFID, video surveillance and other technologies with mobile terminal devices to identify, locate and operate the raw materials and equipment involved in the production process, realize visual scheduling and production traceability, and improve post-processing efficiency.

[0168] The technical solution disclosed in the present invention monitors key parameters in the production process in real time, such as the temperature in the reduction furnace, the concentration of the feed gas, etc., to ensure the stability and controllability of the production process. The system can automatically detect and record key data such as the growth diameter of the silicon rod, providing data support for the optimization of the production process. In combination with the LIMS system and the online analyzer data, an impurity early warning model is provided. According to the material flow and impurity content of the previous process, a historical operation curve model is configured to predict the impurity content of the subsequent process, so as to achieve early warning and control. The threshold setting range is synchronized to the video platform, and the video screen can remind the reduction furnace of abnormal feeding and events in real time. Real-time grasp of inventory status, including the number of silicon rods, pallet information, storage location, production date and other information. Record the transportation information of silicon rods, including shipping batches, transportation routes, transportation time, destination, etc. Through technical means such as GPS, the transportation process is monitored in real time to ensure the safe delivery of silicon rods.

[0169] In addition to real-time online monitoring and early warning of video visualization, it also provides a wealth of visualization reports and charts, such as production progress charts, quality control charts, inventory distribution charts, etc. Relevant personnel can view this information at any time through mobile phones, computers and other terminal devices to improve work efficiency and decision-making accuracy.

[0170] It can record and trace every step in the production process of polysilicon rods, including raw material input, production and processing, quality inspection, packaging and warehousing, etc. Through video, barcode or RFID technology, the full life cycle of silicon rods can be traced to ensure the accuracy and completeness of product information.

[0171] The present disclosure also provides a polysilicon rod production information tracing device, see Figure 2 As shown, the device comprises:

[0172] The first generating module 210 is configured to import the basic information of the silicon powder used to produce the polycrystalline silicon rod as a data field into the label code generating system, and generate first traceability information according to the data field through the label code generating system based on a preset query condition;

[0173] The second generating module 220 is configured to determine the second traceability information of the polycrystalline silicon rod according to the growth information of the polycrystalline silicon rod in the production process and the growth information of the polycrystalline silicon rod historically generated under the same growth conditions as the polycrystalline silicon rod;

[0174] The third generating module 230 is configured to generate third traceability information of the polycrystalline silicon rod according to event information of the polycrystalline silicon rod in the process of transportation and packaging line circulation, and to pop up a window prompt in the inspection system for event information corresponding to the transportation and packaging of the polycrystalline silicon rod according to the third traceability information;

[0175] The fourth generation module 240 is configured to generate and print the production information identification of the polycrystalline silicon rod according to the first traceability information, the second traceability information and the third traceability information of the polycrystalline silicon rod, wherein the production information identification is used to query the production information of the polycrystalline silicon rod.

[0176] In a possible implementation, the second generating module 220 is configured to:

[0177] Based on the growth information of the polycrystalline silicon rod during the production process and the growth information of the polycrystalline silicon rod historically generated under the same growth conditions as the polycrystalline silicon rod;

[0178] Determining whether the growth of the polycrystalline silicon rod is at a critical node according to a growth Pearson correlation coefficient between the polycrystalline silicon rod and the polycrystalline silicon rod historically generated under the same growth conditions;

[0179] If the growth of the polysilicon rod is at the critical node, a critical node label is added to the corresponding monitoring video;

[0180] The second traceability information is generated according to the production information of the polysilicon rods during the production process and the monitoring video corresponding to the key node label.

[0181] In a possible implementation, the growth information includes a growth diameter and a growth length, and the second generating module 220 is configured to:

[0182] Discretizing the growth diameter and the growth length of the polycrystalline silicon rod during the production process according to production time points to obtain the growth diameter and the growth length corresponding to different production time points;

[0183] A first growth Pearson correlation coefficient between the growth diameters of the polycrystalline silicon rods at different production time points during the production process and the growth diameters of the polycrystalline silicon rods historically generated under the same growth conditions as the polycrystalline silicon rods;

[0184] A second growth Pearson correlation coefficient is determined based on the growth length of the polycrystalline silicon rod at different production time points during the production process and the growth length of the polycrystalline silicon rod historically generated under the same growth conditions as the polycrystalline silicon rod.

[0185] In a possible implementation, the second generating module 220 is configured to:

[0186] Acquire a preset first threshold set and a second threshold set, wherein the first threshold set and the second threshold set respectively include a plurality of first thresholds and a plurality of second thresholds;

[0187] Compare a first growth Pearson correlation coefficient between the polycrystalline silicon rod and the polycrystalline silicon rod historically generated under the same growth conditions with a plurality of the first thresholds in the first threshold set to obtain a first comparison result;

[0188] Compare a second growth Pearson correlation coefficient between the polycrystalline silicon rod and the polycrystalline silicon rod historically generated under the same growth conditions with a plurality of the second thresholds in the second threshold set to obtain a second comparison result;

[0189] Whether the growth of the polycrystalline silicon rod is at a critical node is determined according to the first comparison result and the second comparison result.

[0190] In a possible implementation, the third generating module 230 is configured as follows:

[0191] Generate production events according to event information of the polycrystalline silicon rods during production, transportation and packaging line circulation;

[0192] Determining whether the production event of the polycrystalline silicon rod is an abnormal event;

[0193] If the production event of the polycrystalline silicon rod is an abnormal event, an abnormal label is marked on the monitoring video of the polycrystalline silicon rod during the production, transportation and packaging process;

[0194] The third traceability information of the polycrystalline silicon rod is generated according to the abnormal label of the polycrystalline silicon rod and the monitoring video marked with the abnormal label.

[0195] In a possible implementation, the third generating module 230 is configured as follows:

[0196] According to the temperature in the reduction furnace, the concentration of the feed gas, the material flow rate and the impurity content of the polycrystalline silicon rods in the previous process, a historical operation curve model is configured to predict the predicted impurity content of the polycrystalline silicon rods in the subsequent process;

[0197] Determining whether the impurity content of the polycrystalline silicon rod is abnormal in each of the processes according to the predicted impurity content of each of the processes and the corresponding impurity content threshold value set for each of the processes;

[0198] The real-time images, historical personnel operation records, quality information retrieval records and equipment status monitoring information of the polycrystalline silicon rods during the transportation and packaging line flow are stored in an event information database;

[0199] Identify the real-time images, historical personnel operation records, quality information retrieval records and equipment status monitoring information to determine whether there are any information anomalies;

[0200] Whether the production event of the polycrystalline silicon rod is an abnormal event is determined according to the first result of whether the impurity content of the polycrystalline silicon rod is abnormal in each of the processes and the second result of whether the information is abnormal.

[0201] In a possible implementation, the third generation module 230 is configured to obtain the historical operation curve model by training in the following manner:

[0202] Construct a regression equation: I = β0 + β1T + β2C + β3*F + ε, wherein I is the impurity content, T is the temperature in the reduction furnace, C is the concentration of the feed gas, F is the material flow rate of the polysilicon rod in the previous process, β0 is the intercept term, β1, β2, β3 are regression coefficients, and ε is the error term;

[0203] According to the temperature in the reduction furnace corresponding to the polycrystalline silicon rods produced historically, the concentration of the feed gas, the material flow rate and the impurity content of the polycrystalline silicon rods in the previous process, the least squares method is used to estimate the intercept term β0, the regression coefficient β1, the regression coefficient β2 and the regression coefficient β3 of the regression equation;

[0204] When the intercept term β0, the regression coefficient β1, the regression coefficient β2 and the regression coefficient β3 of the regression equation are determined, the model parameters are adjusted through cross-validation to obtain the historical operation curve model.

[0205] The present disclosure also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the method described in any one of the aforementioned embodiments are implemented.

[0206] The present disclosure also provides an electronic device, including:

[0207] a memory having a computer program stored thereon;

[0208] A processor is used to execute the computer program in the memory to implement the steps of the method in any one of the aforementioned embodiments.

[0209] Figure 3 The polycrystalline silicon rod production information tracing device 100 shown includes: a processor 1001 and a memory 1003. Among them, the processor 1001 and the memory 1003 are connected, such as through a bus 1002. Optionally, the polycrystalline silicon rod production information tracing device 100 may also include a communication component 1004, and the communication component 1004 can be used for data interaction between the device 100 and other devices, such as data transmission and / or data reception. It should be noted that in actual scheduling, the communication component 1004 is not limited to one, and the structure of the polycrystalline silicon rod production information tracing device 100 does not constitute a limitation on the embodiments of the present application.

[0210] Processor 1001 may be a CPU (Central Processing Unit), a general purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 1001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0211] The bus 1002 may include a path to transmit information between the above components. The bus 1002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 1002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0212] The memory 1003 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), magnetic disk storage medium, other magnetic storage devices, or any other medium that can be used to carry or store program code and can be read by a computer, without limitation herein.

[0213] The memory 1003 is used to store program codes for executing the embodiments of the present disclosure, and the execution is controlled by the processor 1001. The processor 1001 is used to execute the program codes stored in the memory 1003 to implement the steps shown in the embodiment of the polycrystalline silicon rod production information tracing method.

[0214] The embodiment of the present disclosure also provides a computer-readable storage medium having program code stored thereon. When the program code is executed by a processor, the steps and corresponding contents of the aforementioned polycrystalline silicon rod production information traceability method embodiment can be implemented.

[0215] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments; within the technical concept of the present disclosure, various changes, modifications, substitutions and variations may be made to these embodiments, and these changes, modifications, substitutions and variations all fall within the protection scope of the present disclosure.

[0216] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any appropriate manner without contradiction, and they should also be regarded as the contents disclosed in this disclosure. In order to avoid unnecessary repetition, this disclosure will not further describe various possible combinations. The technical scope of this application is not limited to the contents in the specification, and its technical scope must be determined according to the scope of the claims.

Claims

1. A method for tracing production information of polysilicon rods, characterized in that: The method comprises: Importing basic information of silicon powder used to produce the polysilicon rods as a data field into a label code generation system, and generating first traceability information according to the data field through the label code generation system based on a preset query condition; Determine second traceability information of the polycrystalline silicon rod according to growth information of the polycrystalline silicon rod during the production process and growth information of the polycrystalline silicon rod historically generated under the same growth conditions as the polycrystalline silicon rod; According to the event information of the polycrystalline silicon rods in the process of production, transportation and packaging line circulation, third traceability information of the polycrystalline silicon rods is generated, and according to the third traceability information, event information corresponding to the transportation and packaging of the polycrystalline silicon rods is prompted in a pop-up window in the inspection system; A production information identification of the polycrystalline silicon rod is generated and printed according to the first traceability information, the second traceability information and the third traceability information of the polycrystalline silicon rod, wherein the production information identification is used to query the production information of the polycrystalline silicon rod.

2. The method for tracing the production information of polycrystalline silicon rods according to claim 1, characterized in that: The determining the second traceability information of the polycrystalline silicon rod according to the growth information of the polycrystalline silicon rod in the production process and the growth information of the polycrystalline silicon rod historically generated under the same growth conditions as the polycrystalline silicon rod comprises: Based on the growth information of the polycrystalline silicon rod during the production process and the growth information of the polycrystalline silicon rod historically generated under the same growth conditions as the polycrystalline silicon rod; Determining whether the growth of the polycrystalline silicon rod is at a critical node according to a growth Pearson correlation coefficient between the polycrystalline silicon rod and the polycrystalline silicon rod historically generated under the same growth conditions; If the growth of the polysilicon rod is at the critical node, a critical node label is added to the corresponding monitoring video; The second traceability information is generated according to the production information of the polysilicon rods during the production process and the monitoring video corresponding to the key node label.

3. The method for tracing the production information of polycrystalline silicon rods according to claim 2, characterized in that: The growth information includes a growth diameter and a growth length, and the growth Pearson correlation coefficient between the growth information of the polycrystalline silicon rod during the production process and the growth information of the polycrystalline silicon rod historically generated under the same growth conditions of the polycrystalline silicon rod includes: Discretizing the growth diameter and the growth length of the polycrystalline silicon rod during the production process according to production time points to obtain the growth diameter and the growth length corresponding to different production time points; A first growth Pearson correlation coefficient between the growth diameters of the polycrystalline silicon rods at different production time points during the production process and the growth diameters of the polycrystalline silicon rods historically generated under the same growth conditions as the polycrystalline silicon rods; A second growth Pearson correlation coefficient is determined based on the growth length of the polycrystalline silicon rod at different production time points during the production process and the growth length of the polycrystalline silicon rod historically generated under the same growth conditions as the polycrystalline silicon rod.

4. The method for tracing the production information of polysilicon rods according to claim 3, characterized in that: The determining whether the growth of the polycrystalline silicon rod is at a critical node according to the growth Pearson correlation coefficient between the polycrystalline silicon rod and the polycrystalline silicon rod historically generated under the same growth conditions comprises: Acquire a preset first threshold set and a second threshold set, wherein the first threshold set and the second threshold set respectively include a plurality of first thresholds and a plurality of second thresholds; Compare a first growth Pearson correlation coefficient between the polycrystalline silicon rod and the polycrystalline silicon rod historically generated under the same growth conditions with a plurality of the first thresholds in the first threshold set to obtain a first comparison result; Compare a second growth Pearson correlation coefficient between the polycrystalline silicon rod and the polycrystalline silicon rod historically generated under the same growth conditions with a plurality of the second thresholds in the second threshold set to obtain a second comparison result; Whether the growth of the polycrystalline silicon rod is at a critical node is determined according to the first comparison result and the second comparison result.

5. The method for tracing the production information of polysilicon rods according to claim 1, characterized in that: The generating of the third traceability information of the polycrystalline silicon rod according to the event information of the polycrystalline silicon rod in the process of production, transportation and packaging line circulation includes: Generate production events according to event information of the polycrystalline silicon rods during production, transportation and packaging line circulation; Determining whether the production event of the polycrystalline silicon rod is an abnormal event; If the production event of the polycrystalline silicon rod is an abnormal event, an abnormal label is marked on the monitoring video of the polycrystalline silicon rod during the production, transportation and packaging process; The third traceability information of the polycrystalline silicon rod is generated according to the abnormal label of the polycrystalline silicon rod and the monitoring video marked with the abnormal label.

6. The method for tracing the production information of polycrystalline silicon rods according to claim 5, characterized in that: The determining whether the production event of the polycrystalline silicon rod is an abnormal event comprises: According to the temperature in the reduction furnace, the concentration of the feed gas, the material flow rate and the impurity content of the polycrystalline silicon rods in the previous process, a historical operation curve model is configured to predict the predicted impurity content of the polycrystalline silicon rods in the subsequent process; Determining whether the impurity content of the polycrystalline silicon rod is abnormal in each of the processes according to the predicted impurity content of each of the processes and the corresponding impurity content threshold value set for each of the processes; The real-time images, historical personnel operation records, quality information retrieval records and equipment status monitoring information of the polycrystalline silicon rods during the transportation and packaging line flow are stored in an event information database; Identify the real-time images, historical personnel operation records, quality information retrieval records and equipment status monitoring information to determine whether there are any information anomalies; Whether the production event of the polycrystalline silicon rod is an abnormal event is determined according to the first result of whether the impurity content of the polycrystalline silicon rod is abnormal in each of the processes and the second result of whether the information is abnormal.

7. The method for tracing the production information of polycrystalline silicon rods according to claim 6, characterized in that: The historical operation curve model is obtained by training in the following way: Construct a regression equation: I=β0+β1T+β2C+β3*F+ε, wherein I is the impurity content, T is the temperature in the reduction furnace, C is the concentration of the feed gas, F is the material flow rate of the polycrystalline silicon rod in the previous process, β0 is the intercept term, β1, β2, β3 are regression coefficients, and ε is the error term; According to the temperature in the reduction furnace corresponding to the polycrystalline silicon rods produced historically, the concentration of the feed gas, the material flow rate and the impurity content of the polycrystalline silicon rods in the previous process, the least squares method is used to estimate the intercept term β0, the regression coefficient β1, the regression coefficient β2 and the regression coefficient β3 of the regression equation; When the intercept term β0, the regression coefficient β1, the regression coefficient β2 and the regression coefficient β3 of the regression equation are determined, the model parameters are adjusted through cross-validation to obtain the historical operation curve model.

8. A polysilicon rod production information tracing device, characterized in that: The device comprises: A first generating module is configured to import basic information of silicon powder used to produce the polycrystalline silicon rod as a data field into a label code generating system, and based on a preset query condition, generate first traceability information according to the data field through the label code generating system; A second generating module is configured to determine second traceability information of the polycrystalline silicon rod according to growth information of the polycrystalline silicon rod in the production process and growth information of the polycrystalline silicon rod historically generated under the same growth conditions as the polycrystalline silicon rod; A third generating module is configured to generate third traceability information of the polycrystalline silicon rod according to event information of the polycrystalline silicon rod in the process of transportation and packaging line circulation, and to pop up a window prompt in the inspection system for event information corresponding to the transportation and packaging of the polycrystalline silicon rod according to the third traceability information; The fourth generation module is configured to generate and print the production information identification of the polycrystalline silicon rod according to the first traceability information, the second traceability information and the third traceability information of the polycrystalline silicon rod, wherein the production information identification is used to query the production information of the polycrystalline silicon rod.

9. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.

Images