An alarm method, electronic device and computer readable storage medium

Abstract

The application discloses an alarm method, an electronic device and a computer readable storage medium. The alarm method is realized through an alarm system, which can include a data acquisition module, an abnormal rule engine module, a sentinel robot scheduling module, an intelligent push execution module and a closed-loop tracking and statistics module. The data acquisition module acquires production data of a single crystal furnace. The abnormal rule engine module can determine that the produced crystal has a quality abnormality and / or the single crystal furnace has a timeout abnormality based on the production data. The quality abnormality indicates that the quality of the crystal produced by the single crystal furnace is abnormal. The timeout abnormality indicates that the operation time of a target step in the crystal production process is abnormal. The intelligent push execution module can push an alarm message matched with the existing abnormality to a corresponding EC group through the sentinel robot scheduling module to realize timely alarm. In addition, the alarm state corresponding to the existing abnormality can be updated through the closed-loop tracking and statistics module to realize timely update of the state.

Description

Technical Field

[0001] This application relates to the field of computer technology, specifically to an alarm method, electronic device, and computer-readable storage medium. Background Technology

[0002] When preparing crystals (such as photovoltaic crystals) in a single crystal furnace, a series of steps must be completed in sequence, including melting, crystal pulling, shoulder forming, diameter equalization, finishing, and crystal removal. Various abnormalities are prone to occur during the operation of the single crystal furnace and the execution of the process. At present, problems are mainly identified through manual inspection, which not only makes it difficult to detect faults in a timely manner, but also causes delays in alarms and handling, interferes with the normal operation of the equipment, and ultimately reduces the overall production efficiency. Summary of the Invention

[0003] This application provides an alarm method, electronic device, and computer-readable storage medium, which aim to improve the timeliness of anomaly detection, thereby improving the timeliness of alarms, and further enabling timely handling of anomalies, ensuring the normal operation of the single crystal furnace, and improving the production efficiency of the single crystal furnace.

[0004] Firstly, this application provides an alarm method, including: Obtain production data from the single crystal furnace; Based on the production data, it is determined that the single crystal furnace has quality abnormalities (i.e., the crystals produced by the single crystal furnace have quality abnormalities) and / or timeout abnormalities. Among them, quality abnormality indicates that the quality of the crystals produced by the single crystal furnace is abnormal; timeout abnormality indicates that the operation time of the target step in the crystal production process exceeds the time limit. Generate alarm messages that match existing anomalies, and push alarm messages based on existing anomalies.

[0005] In one possible design approach, quality anomalies include lifespan anomalies; Based on production data, it was determined that there were quality abnormalities in the single crystal furnace, including: Obtain the lifespan of crystals (or single crystals) pulled in a single crystal furnace from production data; If the lifespan of the crystal is less than the first lifespan, and the crystal is pulled from silicon material at the bottom of a non-single crystal furnace, then the crystal produced by the single crystal furnace is determined to have an abnormal lifespan.

[0006] In one possible design approach, the lifetime of the crystal is obtained by detecting the first target position of the first crystal pulled after re-casting.

[0007] In one possible design approach, quality anomalies include high oxygen anomalies; Based on production data, it was determined that there were quality abnormalities in the single crystal furnace, including: Obtain the oxygen content value at the second target position of the first crystal pulled after the single crystal furnace is restarted from the production data; If the oxygen content of the crystal is greater than the first content value, and the crystal is pulled from silicon material at the bottom of a non-single crystal furnace, then it is determined that the crystal produced by the single crystal furnace has an abnormally high oxygen content.

[0008] In one possible design approach, an alarm message matching the existing anomaly is generated, including: If a quality anomaly exists and no alarm message matching the quality anomaly has been pushed, an alarm message matching the quality anomaly will be generated. If an alarm message matching the quality anomaly has been pushed to the single crystal furnace, no alarm message matching the quality anomaly will be generated.

[0009] In one possible design approach, the target process step includes at least one of the following steps: crystal picking, removing the barrel, and cleaning the sub-chamber; Timeout anomalies include at least one of the following: crystal picking timeout anomaly, barrel ejection timeout anomaly, and cleaning auxiliary chamber timeout anomaly.

[0010] In one possible design approach, timeout exceptions include crystal retrieval timeout exceptions; Based on production data, it was determined that the single crystal furnace had a timeout anomaly, including: The duration of the isolation step and the weight of the crystal are determined based on production data; where the crystal weight represents the weight of the pulled crystal. If the continuous operation time of the isolation step reaches the first time, and the crystal weight is continuously greater than the first weight during the continuous operation time, then it is determined that there is a crystal taking timeout abnormality in the single crystal furnace.

[0011] In one possible design approach, timeout exceptions include cleaning auxiliary compartment timeout exceptions; Based on production data, it was determined that the single crystal furnace had a timeout anomaly, including: Obtain the continuous operation time and auxiliary chamber status of the last barrel extraction step from the production data; If the continuous operation time of the last cylinder lifting step reaches the second time, and the auxiliary chamber status indicator is not turned off when the second time is reached, it is determined that there is an abnormality in the cleaning auxiliary chamber.

[0012] In one possible design approach, alert messages are pushed based on existing anomalies, including: Push alarm messages to the robots in the workgroups corresponding to the anomalies; The alert message was sent to the work group via a robot; The robot notifies the relevant person in charge of handling any anomalies in the work group.

[0013] In one possible design approach, the alarm status corresponding to an existing exception is updated, including: The alarm status is updated based on the push status of the alarm message and the status of any abnormal rectification. The alarm status includes multiple states such as pending push, pushed, in process, and in process.

[0014] Secondly, this application also provides an alarm system, including: The data acquisition module is used to obtain production data from the single crystal furnace; An anomaly determination module is used to determine, based on the production data, that the single crystal furnace has quality anomalies and / or timeout anomalies; wherein, the quality anomaly indicates that the quality of the crystals produced by the single crystal furnace is abnormal; and the timeout anomaly indicates that the operation time of the target step in the crystal production process exceeds the time limit. The alarm message push module is used to generate alarm messages that match existing anomalies, and push the alarm messages based on the existing anomalies.

[0015] The status update module is used to update the alarm status corresponding to existing anomalies.

[0016] Thirdly, this application also provides an alarm method, including: Obtain production data from the single crystal furnace; Based on the production data, it was determined that the crystals produced by the single crystal furnace had quality abnormalities. The quality anomaly indicates that the quality of the crystals produced by the single crystal furnace is abnormal; Generate alarm messages that match existing anomalies, and push the alarm messages based on the existing anomalies; Update the alarm status corresponding to the existing anomaly.

[0017] Fourthly, this application also provides an alarm method, including: Obtain production data from the single crystal furnace; Based on the production data, it was determined that the single crystal furnace had a timeout anomaly. The timeout exception refers to the abnormal operation time of the target step in the crystal production process. Generate alarm messages that match existing anomalies, and push the alarm messages based on the existing anomalies; Update the alarm status corresponding to the existing anomaly.

[0018] Fifthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the alarm method described above.

[0019] Sixthly, this application also provides a computer program product, including a computer program or instructions, which, when executed by a processor, implement the alarm method described above. In a seventh aspect, this application also provides an electronic device, comprising: a memory having a computer program stored thereon; and a processor for executing the computer program in the memory to implement the alarm method described above.

[0020] Beneficial effects: In this application, considering the potential for abnormalities in auxiliary processes during crystal production after furnace startup and the potential defects in the final product quality of the single crystal furnace, production data is used to determine whether the single crystal furnace exhibits quality abnormalities and / or timeout abnormalities. Quality abnormalities indicate that the quality of the crystals produced by the single crystal furnace is abnormal, while timeout abnormalities indicate that the operation time of the target step in the crystal production process exceeds the allowed time. This enables automatic detection of abnormalities such as finished product quality abnormalities after crystal production and time-limit exceeding abnormalities in supporting processes. It allows for refined classification and targeted monitoring based on the production stage and fault type where abnormalities occur, covering the entire process from auxiliary processes during furnace operation to finished product inspection. This comprehensive coverage and detection of abnormalities related to single crystal production ensures rapid alarms for abnormal events, facilitating timely fault handling by staff, maintaining stable operation of the single crystal furnace, ensuring efficient crystal production, and effectively improving production efficiency. Furthermore, the alarm status corresponding to the abnormality is updated in real time, completing closed-loop management of the entire alarm process, allowing relevant personnel to monitor the progress of abnormalities in real time, further improving fault handling efficiency.

[0021] Other features and advantages of this application will be described in detail in the following detailed description section. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a schematic diagram of the structure of the alarm system provided in the exemplary embodiments of this disclosure; Figure 2 This is a flowchart illustrating an alarm method provided by an exemplary embodiment of this disclosure. Figure 1 ; Figure 3 This is a flowchart illustrating an alarm method provided by an exemplary embodiment of this disclosure. Figure 2 ; Figure 4 This is a schematic diagram of an alarm message provided by an exemplary embodiment of this disclosure; Figure 5This is a flowchart illustrating an alarm method provided by an exemplary embodiment of this disclosure. Figure 3 ; Figure 6 This is a schematic diagram of the structure of an electronic device provided by an exemplary embodiment of this disclosure. Detailed Implementation

[0024] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0025] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0026] "A and / or B" includes the following three combinations: A only, B only, and a combination of A and B.

[0027] The use of "applies to" or "configured to" in this application implies open and inclusive language, which does not exclude the applicability to or configuration to devices performing additional tasks or steps. Additionally, the use of "based on" implies openness and inclusivity, because processes, steps, calculations, or other actions "based on" one or more of the stated conditions or values ​​may in practice be based on additional conditions or values ​​beyond those stated.

[0028] In this application, the term "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0029] In the photovoltaic crystal production process, equipment (such as monocrystalline furnaces) needs to be managed to detect and resolve any abnormalities. Traditional management models have several drawbacks: production anomalies rely primarily on manual inspections and hierarchical reporting, resulting in limited information collection methods and making it difficult for managers to monitor on-site conditions in real time; the rectification process lacks a closed-loop tracking system, leading to interruptions and missed issues, causing recurring violations; and all production reports are manually compiled, resulting in low efficiency and data inaccuracies. The overall management model is highly dependent on personnel experience, failing to achieve digital and proactive control.

[0030] Therefore, this application provides an alarm system based on an exception control (EC) swarm sentinel robot, which can automatically identify production anomalies (such as quality anomalies and timeout anomalies), classify the identified anomalies into alarm levels, and match differentiated push rules according to the level. Here, EC can refer to an employee communication and office automation integrated software system. Correspondingly, an EC swarm can be understood as a group chat within the installed EC software. Through the EC swarm robot, the system automatically distributes graded messages, intercepts duplicate alarms, and provides status feedback on the handling process, achieving intelligent distribution of anomalies by swarm, effectively improving the accuracy and readability of alarm information, and meeting the real-time alarm requirements of manufacturing production monitoring, equipment maintenance, and other scenarios. For example, this system can be used in monocrystalline silicon production scenarios, enabling real-time monitoring and alarm push of the operating conditions and quality during monocrystalline silicon production. Furthermore, for quality anomalies and timeout anomalies, the alarm system provides closed-loop handling throughout the process, suppressing duplicate alarms and avoiding message bombardment. In addition, the alarm system can regularly generate and push daily, weekly, and monthly statistical reports to provide data support for management decisions, thereby reducing the incidence of anomalies such as quality defects and timeouts, shortening the time for problem rectification, and improving equipment uptime and overall production efficiency.

[0031] For example, such as Figure 1 As shown, the alarm system may include a data acquisition module, an anomaly rule engine module, a sentinel robot scheduling module, an intelligent push execution module, and a closed-loop tracking and statistics module.

[0032] The data acquisition module interfaces with production databases (such as manufacturing execution systems (MES)), production databases, and server interfaces to collect production data such as machine status, process parameters, and quality indicators in real time or periodically.

[0033] The exception rule engine module has rules for quality exception judgment, timeout exception judgment, and continuous exception judgment, and automatically determines whether to trigger an alarm.

[0034] The Sentinel Robot Scheduling Module establishes a communication connection with the EC Group Robot API to complete message encapsulation, permission verification, group routing, and sending control.

[0035] The intelligent push execution module sends real-time alarms to the corresponding EC workgroups according to the anomaly level, and automatically pushes daily, weekly and monthly reports at fixed times.

[0036] The closed-loop tracking and statistics module records alarm status, rectification status, and processing time to achieve closed-loop management. It also automatically calculates the anomaly rate, rectification rate, and improvement time.

[0037] The aforementioned alarm system can execute alarm methods. For example, this alarm system can be an electronic device. That is, the entity executing the alarm method can be an electronic device. The following will combine... Figure 2 The process of pushing alarms is described in detail. For example... Figure 2 As shown, alarm methods may include: S201, Obtain production data from the single crystal furnace.

[0038] In this embodiment, the required production data is obtained from the growth records of the single crystal furnace to determine whether there are any production anomalies such as quality abnormalities or timeouts, thereby achieving anomaly monitoring. For example, relevant data such as machine status and quality indicators can be obtained in real time or periodically from production databases such as the MES system.

[0039] S202. Based on production data, determine whether there are quality abnormalities in the crystals produced by the single crystal furnace and / or whether there are timeout abnormalities in the single crystal furnace.

[0040] A quality anomaly indicates that the crystal produced by the single crystal furnace has an abnormal quality, i.e., a defect. Optionally, a quality anomaly includes a lifetime anomaly (or described as a low lifetime red line) and / or a high oxygen anomaly (or described as a high oxygen red line). The low lifetime red line is defined as: the lifetime value at a specific position after the single crystal is cut off (the first target position as described below) is lower than a set standard value.

[0041] The high oxygen red line is defined as the oxygen content value at a specific location (the second target location as described below) after the single crystal is truncated being higher than a set standard value.

[0042] A timeout exception (or timeout error) indicates that the operation time of a target step in the crystal production process has exceeded the set time limit. Optionally, a timeout exception is defined as an exception where the target step has reached its set standard operation time and no termination condition has been identified.

[0043] In this embodiment, the electronic device uses production data, combined with quality anomaly judgment rules, to determine whether the quality of the crystals produced by the single crystal furnace is abnormal, thereby detecting whether there is a quality anomaly in the single crystal furnace. Furthermore, it uses production data, combined with timeout anomaly judgment rules, to determine whether the crystals in the single crystal furnace have exceeded the target step operation time in the production process, thereby detecting whether there is a timeout anomaly in the single crystal furnace.

[0044] The two types of anomalies described in this application—timeout anomalies and quality anomalies—are examples of time-limited anomalies occurring during auxiliary processes in crystal production after furnace start-up. Timeout anomalies refer to anomalies caused by exceeding time limits in auxiliary processes supporting production. Quality anomalies, on the other hand, refer to finished product quality anomalies detected during finished product inspection after the crystals have exited the furnace. This approach, by finely classifying and targeting the production stage and fault type of anomalies, covers the entire process from auxiliary processes to finished product inspection, achieving comprehensive coverage and detection of anomalies related to single crystal production.

[0045] The following section will first detail the above-mentioned content on quality anomaly judgment, and then introduce the content on timeout anomaly judgment.

[0046] In some embodiments, quality abnormalities include lifespan abnormalities and / or high oxygen abnormalities. The process for determining lifespan abnormalities will be described first, followed by the process for determining high oxygen abnormalities.

[0047] The process of determining abnormal lifetimes may include obtaining the lifetime of crystals pulled in a single-crystal furnace from production data. The lifetime of a crystal refers to its minority carrier lifetime, which is determined by the crystal lattice quality and electrical properties. Excessive crystal defects and impurities will result in a low minority carrier lifetime. A crystal lattice is a spatial structure formed by the periodic and regular arrangement of atoms within a crystal.

[0048] If the crystal's lifetime is less than the first lifetime, and the crystal is pulled from silicon material from a non-single-crystal furnace, then the crystal produced by the single-crystal furnace is determined to have a lifetime anomaly, triggering the low lifetime warning line. However, if the crystal's lifetime is greater than or equal to the first lifetime (e.g., 2000 μs), or if the crystal is pulled from silicon material from the bottom of a single-crystal furnace, then there is no lifetime anomaly.

[0049] When the lifespan of a crystal is less than the first lifespan, it indicates that the crystal's lifespan may be abnormal. If the crystal is pulled from silicon material that is not from the bottom of a single-crystal furnace, it indicates that the crystal is a non-bottom-crystal single crystal. Therefore, it can be determined that the low lifespan of the crystal is not due to the quality of the silicon material, and thus, the crystal's lifespan is abnormal.

[0050] If the crystal is pulled from silicon material at the bottom of the single crystal furnace, it indicates that the crystal is a bottom-crystal single crystal. Therefore, the low lifespan of the crystal is due to the quality of the silicon material, not the single crystal furnace. Thus, the lifespan of the crystal can be determined to be normal.

[0051] It should be noted that the silicon material at the bottom of the furnace is constantly exposed to a high-temperature environment, causing impurities to accumulate continuously. This naturally results in a shorter lifespan for the pulled crystals, which is normal. The impurity content of silicon material outside the furnace bottom is controllable, and its lifespan should meet the standard requirements.

[0052] In one example, the crystal's lifetime is obtained by detecting the first target position of the first crystal pulled after re-pulling. The lifetime value is taken from the center measurement point of the head of the first crystal rod in its unsegmented state after re-pulling, such as the lifetime of the 02 head. The crystal rod head is the first part formed after re-pulling, and its central region is directly affected by the furnace thermal field and crystal pulling process parameters, making it highly sensitive to process fluctuations and equipment anomalies. By fixing the detection position, potential problems can be quickly identified in the early stages of crystal rod production, reducing the output of defective products. At the same time, fixing the detection position can also avoid local random deviations and improve the stability of lifetime anomaly judgment.

[0053] In one example, an electronic device can distinguish whether a single crystal is a non-bottom-crystal single crystal by the last digit of its crystal code (also known as the old single crystal code). When the last digit of the crystal code is a first preset character (such as N or Y), the single crystal is determined to be a non-bottom-crystal single crystal. When the last digit of the crystal code is a second preset character (such as W or V), the single crystal is determined to be a bottom-crystal single crystal.

[0054] In some embodiments, the electronic device can determine whether the current lifetime anomaly is the first time it has been triggered. If it is the first time, it indicates that the lifetime anomaly generated by the single crystal is being identified for the first time, and a corresponding alarm message is generated and pushed out. If the lifetime anomaly has been triggered and pushed out before, it indicates that the lifetime anomaly generated by the single crystal is not being identified for the first time, and the alarm content will not be generated again, thereby suppressing repeated alarms. Specifically, within the monitoring period, an alarm action is executed for the first identified crystal lifetime anomaly, and subsequent repeated detections of the same type of anomaly will not trigger an alarm.

[0055] In general, the rules for triggering an alarm based on low lifespan include: 1) The lifespan at a specific location (which could be the first target location) after crystal truncation is less than 2000 μs. 2) Identifying whether a lifespan alarm is triggered for crystals not at the bottom of the crucible, while no alarm is triggered for single crystals at the bottom of the crucible. 3) Identifying the lifespan of the first single crystal after re-injection. 4) The same single crystal furnace will only alarm once within a monitoring cycle, with the first abnormal lifespan alarm being pushed out.

[0056] In some embodiments, the process for determining the high oxygen anomaly included in the aforementioned quality anomaly may include obtaining the oxygen content value at the second target position of the first crystal pulled after the single crystal furnace is restarted from the production data. If the oxygen content value of the crystal is greater than the first content value, and the crystal is pulled based on silicon material from a non-single crystal furnace bottom, then it is determined that the crystal produced by the single crystal furnace has a high oxygen anomaly.

[0057] Considering that the silicon material at the bottom of the furnace is in a high-temperature environment for a long time, impurities continuously accumulate, resulting in a naturally higher oxygen content in the pulled crystals, which is normal. The impurity content of the silicon material outside the furnace bottom is controllable, and its oxygen content should meet the standard requirements. Therefore, when the oxygen content of the crystal is greater than the first value (e.g., 11), and the crystal is not a single crystal from the bottom of the furnace, it indicates that the high oxygen content is not caused by the silicon material at the bottom of the furnace. Therefore, it can be determined that the crystal pulled from the single crystal furnace has an abnormally high oxygen content, triggering the high oxygen threshold.

[0058] If the oxygen content of the crystal is less than or equal to the first content value, or if the crystal is drawn from silicon material at the bottom of the single crystal furnace (i.e., the crystal is a single crystal visible at the bottom of the crucible), then it is determined that the crystal produced by the single crystal furnace does not have an oxygen high anomaly.

[0059] The process for determining whether a crystal is a single crystal visible at the bottom of the crucible or not can be found in the previous text and will not be repeated here.

[0060] Optionally, the oxygen content value of the crystal is obtained by detecting the second target position of the first crystal pulled after the re-processing. In other words, the crystal oxygen content data is taken from the second target detection position of the first single crystal after the re-processing. Specifically, the second target detection position is the tail of the crystal rod. For example, the single crystal numbered 0100E0 is the first crystal produced after this re-processing. Based on this, by limiting the oxygen content value to the second target position, a unified detection benchmark can be established, eliminating data deviations caused by differences in sampling positions and ensuring the comparability of test results from different furnaces and batches.

[0061] In some embodiments, similar to the preceding description, the electronic device can determine whether the current high oxygen anomaly is the first time it has been triggered. If it is the first time, it indicates that the high oxygen anomaly in the crystal generated by the single crystal is being confirmed for the first time, and a corresponding alarm message is generated and pushed out. If the high oxygen anomaly has been triggered and pushed out before, it indicates that the high oxygen anomaly in the crystal generated by the single crystal is not being confirmed for the first time, and the alarm content will not be generated again, thereby suppressing repeated alarms. Specifically, within the monitoring period, an alarm action is executed for the first identified high oxygen anomaly in the crystal, and no alarm is generated for subsequent repeated detections of the same type of anomaly.

[0062] In one example, the rules for determining the high oxygen level red line may include: 1) The oxygen content at the 01 tail is greater than 11. 2) Identifying whether non-bottom-of-crystal crystals trigger a high oxygen level alarm, while bottom-of-crystal crystals do not trigger an alarm. 3) Identifying the oxygen content at the 01 tail of the first single crystal after re-feeding. 4) The same single crystal furnace triggers an alarm only once within a monitoring cycle, with the first high oxygen level alarm being pushed out.

[0063] The above has introduced the relevant content on quality anomaly judgment. The following will continue to introduce the above-mentioned timeout anomaly judgment, that is, the content of working time overtime anomaly.

[0064] In some embodiments, the target process step includes at least one of crystal removal, barrel removal, and auxiliary chamber cleaning. Crystal removal, barrel removal, and auxiliary chamber cleaning represent steps performed after crystal pulling is completed. Crystal removal refers to the process of lifting the crystal from the main furnace chamber to the auxiliary chamber after a single crystal has been pulled, and then opening the furnace door to remove the finished crystal after the crystal has cooled sufficiently and the furnace pressure has returned to normal.

[0065] Cleaning the auxiliary chamber refers to the process of sweeping, wiping, and removing dust from the interior of the auxiliary chamber, including silicon volatiles, dust, silicon slag, and insulation cotton debris.

[0066] The process of lifting the material cylinder refers to the operation of raising and moving the material cylinder, which is used to hold silicon material and receive surplus and residual material, from inside the furnace to outside the furnace.

[0067] Correspondingly, timeout anomalies include at least one of the following: crystal picking timeout, barrel removal timeout, and auxiliary chamber cleaning timeout. Based on this, the control steps corresponding to timeout anomalies are clearly defined, enabling full-process operation time detection for crystal picking, barrel removal, and auxiliary chamber cleaning, and timely identification of timeout steps.

[0068] In one embodiment, the process for determining the above-mentioned crystal extraction timeout exception may include: obtaining the duration of the isolation step and the crystal weight from the production data. The crystal weight represents the weight of the crystal already pulled in the single crystal furnace. The isolation step refers to the entire interlocked operation of separating the main furnace chamber from the auxiliary chamber and depressurizing and cooling after the crystal pulling is completed.

[0069] If the continuous operation time of the isolation step reaches the first time, and the crystal weight is continuously greater than the first weight during the continuous operation time, it is determined that there is an abnormality in crystal taking in the single crystal furnace.

[0070] If the continuous operation time of the isolation step is less than the first time, or the crystal weight during the continuous operation time is less than the first weight, then it is determined that there is no crystal taking timeout abnormality in the single crystal furnace.

[0071] In this embodiment, the continuous operation time and crystal weight of the isolation step in the crystal picking process are obtained from the production data, so as to determine whether the crystal picking timeout has occurred using the continuous operation time and crystal weight.

[0072] When the isolation step runs continuously for a period of time (e.g., 30 minutes) and the weight of the crystal rod always exceeds the first weight (e.g., 10 kg) during this period, it indicates that a qualified crystal rod has been generated in the furnace. However, if the process does not change downwards for a long time, it can be determined that the single crystal furnace may have problems such as mechanical jamming, valve failure, or abnormal control logic, which can be used to determine that the single crystal furnace has a crystal picking timeout abnormality.

[0073] If the isolation process has not reached the first time, it indicates that the single crystal furnace is in the normal process waiting stage, thus confirming that there is no crystal taking timeout abnormality in the single crystal furnace.

[0074] Alternatively, if the weight of the crystal rod does not exceed the first weight, it indicates that the crystal is still in a normal growth state, thus confirming that there is no abnormality in crystal taking timeout in the single crystal furnace.

[0075] In some embodiments, the criteria for determining a crystal retrieval timeout exception include: if the time for the furnace to perform the isolation step (i.e., the continuous operation time of the isolation step) reaches 30 minutes, and the crystal weight is always greater than 10 kg within 30 minutes, then a crystal retrieval timeout exception is determined.

[0076] Based on this, the accuracy of identifying crystal removal anomalies can be significantly improved by comprehensively judging whether there is a timeout in the single crystal furnace based on the operation time of the process and the weight of the crystal rod. Compared with a single time dimension, this method can significantly improve the accuracy of identifying crystal removal anomalies.

[0077] The above describes the judgment process for the crystal retrieval timeout exception among timeout exceptions. The following will continue to describe the judgment process for the cleaning auxiliary chamber timeout exception among timeout exceptions.

[0078] In some embodiments, the duration of the last barrel ejection step in the ejection barrel and the status of the auxiliary chamber are obtained from production data.

[0079] If the continuous operation time of the last cylinder lifting step reaches the second time limit, and the auxiliary chamber status indicator is not turned off when the second time limit is reached, an auxiliary chamber cleaning anomaly is determined. In simple terms, the rule for determining an auxiliary chamber cleaning anomaly is that if the furnace platform remains in the last cylinder lifting step for 51 minutes and no normal auxiliary chamber rotation is detected, then the auxiliary chamber cleaning timeout is determined.

[0080] If the continuous operation time of the last cylinder lifting step is less than the second time, or if the auxiliary chamber status indicator is turned off when the second time is reached, it is determined that there is no abnormality in the cleaning auxiliary chamber.

[0081] In this embodiment, after crystal extraction, the normal operating sequence is: cleaning the auxiliary chamber, removing the barrel, and resetting the auxiliary chamber (i.e., the auxiliary chamber status indicator is off). When the continuous operating time (i.e., the running time) of the last barrel removal step reaches the second time, and the auxiliary chamber is still not closed at this time, it means that the auxiliary chamber resetting process cannot be entered. This indicates that the jam is not due to a fault in the barrel removal itself, but a fault in the preceding process (i.e., cleaning the auxiliary chamber). When the cleaning of the auxiliary chamber is completed, the auxiliary chamber valve, transmission mechanism, and seals become stuck. On the surface, the process has jumped to the barrel removal, but the residual fault forms a chain of jams, causing the barrel removal action to be unable to be executed. The furnace is stuck at the cleaning of the auxiliary chamber for a long time. Therefore, it can be determined that there is an abnormality in the auxiliary chamber cleaning of the single crystal furnace.

[0082] In one example, the timeout rule for cleaning the auxiliary chamber is: if the furnace platform remains in the last cylinder lifting step for 51 minutes and no ordinary auxiliary chamber vortex is detected at 51 minutes, the timeout for cleaning the auxiliary chamber is triggered.

[0083] Based on this, the system combines process runtime and device status for joint judgment, enabling accurate anomaly localization and preventing false alarms caused by relying solely on runtime.

[0084] The following section will introduce the timeout exceptions mentioned above, including the timeout exceptions for the barrel.

[0085] In some embodiments, the process for determining a barrel ejection timeout exception may include: obtaining the duration of the barrel ejection step from the production data of the single crystal furnace. If this duration exceeds a set time (i.e., the sixth time), a barrel ejection timeout exception is determined to exist. In other words, if the barrel ejection step has reached the set time (e.g., 1 hour) and the process has not yet progressed to the next step, a barrel ejection timeout exception can be determined for the single crystal furnace. Otherwise, no barrel ejection exception is determined to exist.

[0086] In some embodiments, similar to the preceding description, the electronic device can determine whether the current timeout anomaly is the first time it has been triggered. If it is the first time, it indicates that a timeout anomaly in the single crystal furnace is being identified for the first time, and a corresponding alarm message is generated and pushed to the device. If the timeout anomaly has been triggered and pushed to the device previously, it indicates that a timeout anomaly in the single crystal furnace is not being identified for the first time, and the alarm content is not generated again, thereby suppressing repeated alarms. Specifically, within the monitoring period, an alarm action is executed for the first timeout anomaly identified, and no alarms are generated for subsequent repeated detections of the same type of anomaly.

[0087] In some embodiments, the determination of both barrel ejection anomaly and secondary chamber cleaning anomaly includes excessively long barrel ejection step duration and failure to proceed to the next step (secondary chamber retraction step). Therefore, in one case, the two anomalies can be distinguished by a threshold time. The aforementioned sixth time is greater than the second time. When the last barrel ejection step reaches the second time and the secondary chamber retraction step has not yet begun, a secondary chamber cleaning anomaly is determined to exist. When the barrel ejection step reaches the sixth time and the secondary chamber retraction step has not yet begun, a barrel ejection anomaly is determined to exist. Alternatively, when the barrel ejection step reaches the sixth time and the secondary chamber retraction step has not yet begun, both barrel ejection anomaly and secondary chamber cleaning anomaly can be determined simultaneously. Or, if a secondary chamber cleaning anomaly is determined to have been triggered, it indicates that the secondary chamber cleaning anomaly may not yet be resolved; therefore, a secondary chamber cleaning anomaly can be determined to exist.

[0088] In another scenario, the distinction can be made based on the condition of the charging barrel. If there's an anomaly in the barrel ejection step itself, the barrel may become mechanically jammed and unable to move, making it less likely to reach the final barrel ejection step. Therefore, if the single crystal furnace is in the final barrel ejection step when the set time (i.e., the second or sixth time) is reached, it indicates that the barrel has already been ejected, and the anomaly in the barrel ejection step itself is less likely, confirming an issue with the cleaning sub-chamber. Conversely, if the single crystal furnace is not in the final barrel ejection step, an anomaly in the barrel ejection process can be identified.

[0089] The above describes the process for identifying production anomalies in a single crystal furnace. Once an anomaly is confirmed, the electronic equipment can generate an alarm message matching the anomaly. The alarm message generation process will be described below.

[0090] S203. In the event of a quality anomaly and / or a timeout anomaly, generate an alarm message that matches the existing anomaly.

[0091] In this embodiment, when a production anomaly such as a quality abnormality or timeout is detected in the single crystal, a corresponding alarm message is generated. After a quality abnormality is detected in the single crystal, an alarm message matching the abnormality is generated to reconstruct the abnormality scenario, enabling relevant personnel to quickly understand the corresponding quality abnormality based on the alarm message and thus resolve the problem promptly. For example, after a lifetime abnormality is detected in the crystal, an alarm message matching the lifetime abnormality is generated. As another example, after a high oxygen level is detected in the crystal, an alarm message matching the high oxygen level is generated.

[0092] When a timeout occurs in the single crystal furnace, an alarm message matching the timeout is generated to reconstruct the timeout situation. For example, if a crystal picking timeout occurs in the single crystal furnace, an alarm message matching the crystal picking timeout is generated. Similarly, if a barrel ejection timeout occurs in the single crystal furnace, an alarm message matching the barrel ejection timeout is generated. And again, if a cleaning auxiliary chamber timeout occurs in the single crystal furnace, an alarm message matching the cleaning auxiliary chamber timeout is generated.

[0093] Optionally, in some embodiments, the alarm message matching the lifetime abnormality may include multiple of the following: the handler information corresponding to the lifetime abnormality (such as the production team leader), the number of single crystal furnaces with lifetime abnormalities (such as the number of single crystal furnaces with lifetime abnormalities under the responsibility of the production team), the existence of lifetime abnormalities (i.e. alarm status), order type, investigation suggestions, handling suggestions, and abnormal time.

[0094] Here, the order type indicates the object to which the crystal generated by the single crystal furnace is applied, which can be used to determine the lifetime red line.

[0095] For example, the alarm information matching the above-mentioned lifespan anomaly may include: Production team leader: Yang X; The number of furnaces with a lifespan of this production group on that day: 1 furnace (9:00-9:00). Alarm furnace platform: Module 1 - FB44 (F2604B4411); where FB44 (F2604B4411) represents the specific single crystal furnace identifier; Order type: xx; Alarm status: After 7 re-injections, the lifespan of the 02T tank is 894.0 seconds. Recommendations for investigation: Conduct a comprehensive investigation of the process, considering factors such as personnel, machinery, materials, methods, and environment, to identify any abnormalities. Recommended action: Shut down the furnace immediately and rectify the issues according to the "Low Lifespan Investigation Checklist".

[0096] In some embodiments, the alarm message matching the high oxygen anomaly may include multiple of the following: the handler information corresponding to the high oxygen anomaly, the number of single crystal furnaces with the high oxygen anomaly, the existing high oxygen anomaly (i.e., alarm status), the order type, investigation suggestions, handling suggestions, and the anomaly time.

[0097] Here, the order type indicates the object to which the crystal generated by the single crystal furnace is applied, which can be used to determine the oxygen high red line.

[0098] For example, the alarm information matching the above-mentioned abnormal oxygen levels may include: Production team leader: Yang X; Number of oxygen high-red-line furnaces operated by this production group on that day: 4 furnaces (9:00-9:00). Alarm furnace platform: Three modules - GP75 (G2604P7501); Order type: XX; Alarm status: After one re-injection, the oxygen content at 01W was 11.2; Recommendations for investigation: Conduct a comprehensive investigation of the process, considering factors such as personnel, machinery, materials, methods, and environment, to identify any abnormalities. Recommended course of action: Immediately switch the oxygen reduction parameters and simultaneously coordinate with the quality engineer for analysis and rectification.

[0099] Optionally, the alarm message matching the crystal picking timeout exception may include the handler information corresponding to the crystal picking timeout exception, the cumulative number of crystal picking exceptions (or the number of single crystal picking timeout furnaces), the identifier of the single crystal furnace with the crystal picking exception (i.e., the alarm furnace), the running time of the single crystal furnace with the crystal picking timeout exception, the time in the crystal picking step (or the step time), the existing crystal picking timeout exception (i.e., the alarm status), troubleshooting suggestions, handling suggestions, and the exception time.

[0100] For example, the alarm message matching the above-mentioned crystal retrieval timeout exception may include: Production team leader: Yang X; The number of single crystal furnaces that exceeded the timeout limit for this group on that day was 9 (9:00-9:00). Alarm furnace platform: Module 2 - FF08 (2604F0801); Runtime: 171 hours; Work step time: 32.78 min; Alarm status: Single crystal extraction from the furnace has not been completed within 32 minutes; Troubleshooting recommendations: Check for equipment malfunctions or the availability of tooling and fixtures; Recommendation: The process supervisor should confirm the abnormality and handle it immediately.

[0101] Optionally, the alarm message matching the barrel ejection timeout exception includes multiple of the following: the handler information corresponding to the barrel ejection timeout exception, the cumulative number of barrel ejection exceptions (or barrel ejection timeout furnaces), the identifier of the single crystal furnace with the barrel ejection timeout exception (i.e., the alarm furnace), the running time of the single crystal furnace with the barrel ejection timeout exception, the time in the barrel ejection step (or the step time), the existing crystal picking exception (i.e., alarm status), troubleshooting suggestions, handling suggestions, and exception time.

[0102] For example, the alarm message matching the timeout exception raised by the barrel could include: Production team leader: Zhao xx; The number of furnaces that exceeded the time limit by this group on that day was 3 (9:00-9:00). Alarm furnace platform: Module 1 - EB92 (2604B9201); Running time: 282 hours; Work step time: 60.30 min; Alarm status: The furnace platform has been in the charge lifting step for 60 minutes and has not executed the next step; Recommended investigation: Is there a shortage of materials or other abnormalities? Recommended course of action: The process manager should immediately coordinate the supply of raw materials and confirm the abnormality.

[0103] Optionally, the alarm message matching the cleaning sub-chamber anomaly includes multiple of the following: the information of the person handling the cleaning sub-chamber anomaly, the cumulative number of single crystal furnaces with cleaning sub-chamber anomalies (or the number of furnaces with cleaning sub-chamber timeouts), the identifier of the single crystal furnace with cleaning sub-chamber anomaly (i.e., the alarm furnace), the running time of the single crystal furnace with cleaning sub-chamber anomaly, the time in the barrel lifting step (or the step time), the existing cleaning sub-chamber anomaly (i.e., alarm status), troubleshooting suggestions, handling suggestions, and anomaly time.

[0104] For example, the alarm message matching the anomaly in the cleaning sub-room could include: This team cleaned up 5 furnaces that exceeded the time limit in the auxiliary chamber that day (9:00-9:00). Alarm furnace platform: Three modules - GL75 (2604L7501); Runtime: 472 hours; Work step time: 51.25 min; Alarm status: The furnace cleaning chamber has not been completed for more than 51 minutes; Troubleshooting recommendations: Check for equipment malfunctions or the availability of tooling and fixtures; Recommendation: The process supervisor should confirm the abnormality and handle it immediately.

[0105] In some embodiments, for alarm messages that match timeout anomalies, electronic devices can summarize the total number of alarms and related detailed data for the shift in the form of daily reports, automatically count and filter out the furnaces with the top M (e.g., top 5) of time waste ranking, and at the same time complete the comprehensive evaluation of each module, and push daily reports at designated times every day (e.g., 9:30 and 21:30).

[0106] For example, the daily report content is as follows: [Monocrystalline Production Department II (Phase IV) Overtime Report - Night Shift, March 11, 2025] Overall: Number of furnaces that exceeded the time limit during the shift: 21, a decrease compared to the previous shift.

[0107] Module 1: 3, an increase from the previous shift. Among them, 0 exceeded the time limit in the cleaning chamber, 3 exceeded the time limit in the barrel extraction, and 0 exceeded the time limit in the single crystal extraction.

[0108] Module 2: 9, an increase from the previous shift, including 1 timeout in the cleaning chamber, 1 timeout in the barrel extraction, and 7 timeouts in the single crystal extraction.

[0109] Three modules: 2, a decrease from the previous shift, including 2 overtimes in the cleaning chamber, 0 overtimes in the barrel extraction, and 0 overtimes in the single crystal extraction. Four modules: 7, a decrease from the previous shift, including 4 overtimes in the cleaning chamber, 0 overtimes in the barrel extraction, and 3 overtimes in the single crystal extraction.

[0110] Top 5 cases of single crystal pickup timeout on the same day: The longest furnace times were 48.2 min for FA23, 45.02 min for HW89, 44.05 min for FF48, 42.37 min for FF65, and 41.7 min for HT42. Top 5 instances of Qing Deputy's Office exceeding time limits on the same day: The longest furnace times were FE94 (87.57 min), HW27 (74.95 min), HZ09 (69.58 min), GL28 (57.57 min), and HW40 (54.37 min). Top 5 items that exceeded the time limit for material handling on the same day: The longest furnace times were 82.68 min for EB89, 72.22 min for EB92, 66.25 min for FA10, and 61.05 min for EB69.

[0111] Daily report link: Office network link: http: / / xxx.

[0112] Production network link: http: / / xxxxx.

[0113] In this embodiment of the application, any abnormalities existing in the single crystal furnace can be statistically analyzed, reported, and evaluated in at least one of the following forms: daily, weekly, and monthly reports.

[0114] S204. Based on the existing anomalies, push alarm messages.

[0115] In this embodiment of the application, routing can be performed based on the production anomalies existing in the single crystal furnace to push alarm information to the corresponding EC work group.

[0116] In some embodiments, the implementation process of S204 described above may include, for example: Figure 3 S301-S303 are shown.

[0117] S301. Push alarm messages to the robots in the workgroup corresponding to the existing anomalies.

[0118] The work group corresponding to the existing anomaly (i.e., the target work group) can be a work group that matches the production anomaly existing in the single crystal furnace. For example, if the single crystal furnace has a crystal picking timeout anomaly, the route is sent to the target work group corresponding to the crystal picking timeout anomaly to push the alarm message corresponding to the crystal picking timeout anomaly.

[0119] For example, the message can be automatically pushed to the corresponding work group via the EC group robot Webhook interface using a POST method (hypertext transfer protocol secure, HTTPS).

[0120] S302. Send alarm messages in the work group via robot.

[0121] S303. Notify the person responsible for handling the production anomaly via the robot workgroup. For example, such as... Figure 4 As shown, a robot named Crystal Sentinel posted an alert message in the EC workgroup, @YangX. Here, YangX is the person handling the alert.

[0122] Optionally, after generating an alarm message, the alarm message can be structured and encapsulated according to a preset format (such as the JSON format supported by EC robots), and the encapsulated alarm message can be pushed.

[0123] S205. Update the alarm status corresponding to the existing anomaly.

[0124] In this embodiment, the alarm status corresponding to the anomaly in the single crystal furnace is updated to achieve closed-loop tracking of alarms, thereby enabling relevant personnel to clearly understand the latest developments of the anomaly. Additionally, it can suppress repeated alarms.

[0125] In some embodiments, updating the alarm status may include updating the alarm status corresponding to the existing anomaly based on the push status of the alarm message matching the existing anomaly and the rectification status of the existing anomaly. The alarm status may include multiple states such as pending push, pushed, processing, and closed-loop (i.e., processed).

[0126] For example, before an alarm message matching the anomaly is pushed to the corresponding work group, the alarm status corresponding to the anomaly is determined to be "pending push". Once an alarm message matching the anomaly is pushed to the corresponding work group, the alarm status corresponding to the anomaly is determined to be "pushed".

[0127] When an anomaly is detected and is undergoing rectification, meaning the relevant process is resolving the anomaly, the alarm status corresponding to that anomaly is updated to "processing". Specifically, when resolving an anomaly, the handler will perform relevant operations, such as entering handler information; therefore, it can be determined that the anomaly is under rectification. Of course, production data can also be used to determine whether an anomaly is under rectification. This application does not impose any restrictions on the specific methods used to determine whether a detected anomaly is under rectification.

[0128] After determining the rectification results corresponding to the anomaly, the alarm status corresponding to the anomaly can be set to closed loop.

[0129] S206. No alarm message will be generated if there are no quality abnormalities or timeout abnormalities.

[0130] In this embodiment of the application, when there are no quality abnormalities or timeout abnormalities, it indicates that the single crystal furnace is operating normally and no alarm is needed. Then, the production data of the single crystal furnace can continue to be obtained, and the single crystal furnace can continue to be detected for quality abnormalities and / or timeout abnormalities.

[0131] For example, in one scenario, the electronic device determines whether there are quality anomalies and timeout anomalies, thus enabling the detection of multiple anomalies. In another scenario, the electronic device can determine whether there are quality anomalies or timeout anomalies, thus enabling rapid anomaly detection.

[0132] The following will take timeout anomalies, including crystal retrieval timeout anomalies and cleaning auxiliary chamber timeout anomalies, as examples, combined with Figure 5 This section introduces a possible example flow for abnormal alarms. For example... Figure 5 As shown, the process may include: S401. Obtain production data from the single crystal furnace.

[0133] S402. Obtain from the production data the continuous operation time of the isolation step in the crystal extraction process, the crystal weight, the continuous operation time of the last barrel extraction step in the extraction barrel, and the sub-chamber status.

[0134] S403. Determine whether the continuous operation time of the isolation step has reached the first time, and whether the crystal weight is continuously greater than the first weight during the continuous operation time.

[0135] In this embodiment of the application, if the continuous operation time of the isolation step does not reach the first time, or the crystal weight is continuously less than or equal to the first weight during the continuous operation time, it indicates that there is no crystal taking timeout abnormality in the single crystal furnace, and new production data can continue to be read to determine whether there is a timeout abnormality, other abnormalities, etc., that is, S404 can be executed.

[0136] If the continuous operation time of the isolation step reaches the first time, and the crystal weight is continuously greater than the first weight during the continuous operation time, it indicates that there is a crystal taking timeout abnormality in the single crystal furnace, and S405 can be executed.

[0137] S404, Return to S401.

[0138] S405. It has been determined that there is a timeout error in the single crystal furnace.

[0139] S406. Determine whether the continuous operation time of the last cylinder lifting step has reached the second time, and whether the auxiliary chamber status indicates that it is not closed when the second time is reached.

[0140] In this embodiment of the application, if the continuous operation time of the last cylinder removal step does not reach the second time, or if the auxiliary chamber status indicator is turned off when the second time is reached, it indicates that there is no timeout abnormality in the cleaning auxiliary chamber of the single crystal furnace, and new production data can be read to determine whether there is a timeout abnormality, other abnormalities, etc., and S407 can be executed.

[0141] If the continuous operation time of the last cylinder removal step reaches the second time, and the sub-chamber status indicator is not turned off when the second time is reached, it indicates that there is a timeout abnormality in the cleaning sub-chamber of the single crystal furnace, and S408 can be executed.

[0142] S407, Return to S401.

[0143] S408. It has been determined that there is an abnormality in the cleaning sub-chamber of the single crystal furnace.

[0144] S409. Generate an alarm message that matches the existing anomaly.

[0145] S410. Update the alarm status of alarm messages that match existing anomalies to "pending push".

[0146] S411. Push alarm messages to the robots in the workgroup corresponding to the existing anomalies.

[0147] S412. Send alarm messages in the work group via robot.

[0148] S413. Notify the person in charge of handling the anomaly in the work group through the robot.

[0149] S414. Update the alarm status of alarm messages that match existing anomalies to "pushed".

[0150] The implementation process of S401-S414 can be referred to the relevant description above, and will not be repeated here.

[0151] In addition, the detection and alarm process for other anomalies can refer to the detection and alarm process for timeout anomalies.

[0152] In this embodiment, the electronic device can automatically generate various summary reports, such as daily, weekly, and monthly reports, based on production anomalies (e.g., quality anomalies, timeout anomalies) existing in the single crystal furnace, enabling rapid multi-dimensional data retrieval. It also automatically compiles and outputs data on the top k alarms (e.g., top 10) of machines, anomaly rectification rate, and problem improvement trends. The electronic device will push the statistical results to the corresponding EC work group at a specified time each day (e.g., 9:00). Here, Topk refers to the top k single crystal furnaces, production modules, etc., sorted by alarm frequency, anomaly type, etc., and filtered out. Here, k is a positive integer.

[0153] In this embodiment, the architecture of the intelligent push alarm information system can be database-electronic device (such as server)-user terminal. The data acquisition module (such as sensor) saves the collected production data to the database (such as the production database mentioned above). The server periodically or periodically reads production data from the production database and determines whether there are any production anomalies based on the production data. If a production anomaly exists, alarm information matching the production anomaly can be pushed to the target workgroup of the relevant EC software installed on the user terminal, enabling alarm push through the target workgroup.

[0154] It is understandable that the relationship between the module corresponding to the single crystal furnace and the single crystal furnace itself is that the module is a unit that divides the single crystal furnaces into clusters. Each module may include at least one single crystal furnace.

[0155] The above primarily describes the solutions provided by the embodiments of this application from a methodological perspective. It is understood that, in order to achieve the above functions, the electronic device includes hardware structures and / or software modules corresponding to the execution of each function. Based on the units and algorithm steps of the various examples described in the embodiments disclosed in this application, the embodiments of this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by a computer driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the technical solutions of the embodiments of this application.

[0156] This application embodiment can divide the electronic device into functional modules according to the above method example. For example, each function can be divided into its own functional module, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional module. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0157] For example, Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown.

[0158] like Figure 6 As shown, the electronic device 500 may include a processor 510. Optionally, the electronic device may also include a memory 520 and a display screen 530, etc.

[0159] Processor 510 may include one or more processing units, such as application processor (AP), modem processor, graphics processing unit (GPU), image signal processor (ISP), controller, video codec, digital signal processor (DSP), baseband processor, and / or neural network processing unit (NPU). These different processing units may be independent devices or integrated into one or more processors.

[0160] The controller can generate operation control signals based on the instruction opcode and timing signals to complete the control of instruction fetching and execution.

[0161] The processor 510 may also include a memory for storing instructions and data. In some embodiments, the memory in the processor 510 is a cache memory. This memory can store instructions or data that the processor 510 has just used or that are used repeatedly. If the processor 510 needs to use the instruction or data again, it can directly retrieve it from the memory. This avoids repeated accesses, reduces the waiting time of the processor 510, and thus improves the efficiency of the system.

[0162] In some embodiments, the processor 510 may include one or more interfaces. These one or more interfaces can be used to connect the processor 510 to the memory 520, the display 530, and the like.

[0163] In some embodiments of this application, the processor 510 can be used to obtain production data from a single crystal furnace; Based on the production data, it was determined that the single crystal furnace had quality abnormalities and / or timeout abnormalities. Generate alarm messages that match existing anomalies, and push the alarm messages based on the existing anomalies; Update the alarm status corresponding to the existing anomaly.

[0164] The memory 520 can be used to store computer executable program code, which includes instructions. The memory 520 may include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as image playback), etc. The data storage area may store data created during the use of the electronic device 500, etc. The processor 510 executes various functional applications and data processing of the electronic device 500 by running instructions stored in the memory 520 and / or instructions stored in memory located within the processor.

[0165] Electronic device 500 implements display functions through a GPU, display screen 530, and application processor. The GPU is a microprocessor for image processing, connected to the display screen 530 and the application processor. For example, the display screen 530 can be used to configure the aforementioned alarm thresholds, such as the weight threshold, time threshold, etc.

[0166] It should be noted that the above Figure 6 The components shown are merely examples, and this application does not limit the specific components included in the electronic device.

[0167] In some embodiments, the electronic device 500 may be a computer, server, tablet computer, or other device with data processing capabilities.

[0168] It should be understood that each step in the above method embodiments can be completed by integrated logic circuits in the processor hardware or by instructions in software form. The method steps disclosed in the embodiments of this application can be directly manifested as being executed by a hardware processor, or being executed by a combination of hardware and software modules in the processor.

[0169] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0170] Therefore, embodiments of this application provide a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the alarm method described above. Optionally, the computer-readable storage medium may include: a read-only memory, random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0171] For details on the implementation of each of the above operations / steps, please refer to the previous examples, which will not be repeated here.

[0172] In some embodiments, this application also provides a computer program product, including a computer program or instructions that, when executed by a processor, implement the alarm method described above.

[0173] The above provides a detailed description of an alarm method, electronic device, and computer-readable storage medium provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. An alarm method, characterized in that, include: Obtain production data from the single crystal furnace; Based on the production data, it is determined that the crystals produced by the single crystal furnace have quality abnormalities and / or the single crystal furnace has timeout abnormalities. The quality anomaly indicates that the quality of the crystal produced by the single crystal furnace is abnormal; the timeout anomaly indicates that the operation time of the target step in the crystal production process exceeds the timeout. Generate alarm messages that match existing anomalies, and push the alarm messages based on the existing anomalies; Update the alarm status corresponding to the existing anomaly.

2. The method according to claim 1, characterized in that, The quality anomalies include lifespan anomalies; The determination that the crystals produced by the single crystal furnace have quality abnormalities based on the production data includes: The lifespan of the crystal pulled by the single crystal furnace is obtained from the production data; If the lifespan of the crystal is less than the first lifespan, and the crystal is pulled from silicon material at the bottom of a non-single crystal furnace, then it is determined that the crystal produced by the single crystal furnace has an abnormal lifespan.

3. The method according to claim 2, characterized in that, The lifespan of the crystal is obtained by detecting the first target position of the first crystal pulled after re-casting.

4. The method according to any one of claims 1 to 3, characterized in that, The quality anomalies include abnormally high oxygen levels; The determination that the crystals produced by the single crystal furnace have quality abnormalities based on the production data includes: Obtain the oxygen content value at the second target position of the first crystal pulled after the single crystal furnace is restarted from the production data; If the oxygen content of the crystal is greater than the first content value, and the crystal is pulled from silicon material at the bottom of a non-single crystal furnace, then it is determined that the crystal produced by the single crystal furnace has an abnormally high oxygen content.

5. The method according to claim 1 or 2, characterized in that, The target process includes at least one of the following: crystal taking, removing the barrel, and cleaning the auxiliary chamber; The timeout anomaly includes at least one of the following: crystal taking timeout anomaly, barrel ejection timeout anomaly, and cleaning sub-chamber timeout anomaly.

6. The method according to claim 5, characterized in that, The timeout anomalies include crystal extraction timeout anomalies; The determination of a timeout anomaly in the single crystal furnace based on the production data includes: Based on the production data, the duration of the isolation step in the crystal extraction process and the crystal weight are determined; wherein, the crystal weight represents the weight of the pulled crystal. If the continuous operation time of the isolation step reaches a first time, and the weight of the crystal is continuously greater than the first weight during the continuous operation time, then it is determined that the single crystal furnace has a crystal taking timeout abnormality.

7. The method according to claim 5, characterized in that, The timeout anomalies include timeout anomalies in the cleaning auxiliary compartment; The determination of a timeout anomaly in the single crystal furnace based on the production data includes: The continuous operation time and auxiliary chamber status of the last barrel extraction step in the extraction barrel are obtained from the production data. If the continuous operation time of the last cylinder lifting step reaches the second time, and the auxiliary chamber status indicator is not turned off when the second time is reached, it is determined that there is an abnormality in the cleaning auxiliary chamber.

8. The method according to claim 1 or 2, characterized in that, The alarm message pushed based on the existing anomalies includes: The alarm message is pushed to the robots in the workgroup corresponding to the anomaly. The alarm message is sent to the work group via the robot. The robot notifies the person in charge of handling any anomalies in the work group.

9. The method according to claim 1 or 2, characterized in that, Updating the alarm status corresponding to the existing anomaly includes: Based on the push status of the alarm message and the existing abnormal rectification status, the alarm status is updated; wherein, the alarm status includes multiple states such as pending push, pushed, processing, and processing.

10. An electronic device, characterized in that, include: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the alarm method as described in any one of claims 1 to 9.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the alarm method as described in any one of claims 1 to 9.

Images