Boron-boron vacuum pump abnormal early warning method, device, computer equipment and medium

Abstract

This application relates to a method, apparatus, computer equipment, and medium for early warning of abnormalities in a boron expansion vacuum pump. The method includes: acquiring real-time attribute data affecting pump speed during the operation of the boron expansion equipment; obtaining a predicted pump speed value for the boron expansion vacuum pump based on the real-time attribute data and the correspondence between the attribute data and pump speed; obtaining the actual pump speed value of the boron expansion vacuum pump; and pushing an abnormality warning message if the absolute value of the deviation between the predicted pump speed value and the actual pump speed value is greater than a preset safety deviation. In this scheme, since the correspondence between attribute data and pump speed is obtained based on correlation and mechanism analysis of historical process data, the corresponding predicted pump speed value can be accurately obtained based on the real-time acquired attribute data. Then, based on the deviation between the predicted value and the actual value, an early warning judgment can be made, ultimately achieving accurate early warning of abnormalities in the boron expansion vacuum pump.

Description

Technical Field

[0001] This application relates to the field of boron expansion equipment technology, and in particular to a method, device, computer equipment, storage medium and computer program product for early warning of abnormalities in a boron expansion vacuum pump. Background Technology

[0002] Photovoltaic equipment essentially processes raw silicon wafers to produce finished solar cells. In a complete photovoltaic system, the boron diffusion process completes the boron atom diffusion process on the N-type silicon wafer to form PN junctions. The quality of this process has a significant impact on the power generation efficiency of the final solar cells.

[0003] Practice has shown that the vacuum pump system of boron expansion equipment is one of the key components affecting the quality of solar cell processing. Because the boron expansion process produces white solid powder, it can clog the vacuum pump and its pipeline system, resulting in uneven gas distribution in the cavity during the vacuuming process, which seriously affects the quality of solar cell processing.

[0004] However, there is currently no abnormal early warning scheme for the vacuum pump system of boron expansion equipment in traditional technology. Summary of the Invention

[0005] Therefore, it is necessary to provide an accurate method, device, computer equipment, storage medium, and computer program product for early warning of abnormalities in boron diffuser vacuum pumps, addressing the aforementioned technical problems.

[0006] Firstly, this application provides a method for early warning of abnormalities in a boron diffuser vacuum pump. The method includes:

[0007] Obtain real-time attribute data affecting pump speed during the operation of the boron expansion equipment;

[0008] Based on the real-time attribute data and the correspondence between the attribute data and the pump speed, the predicted pump speed of the boron diffusion vacuum pump is obtained.

[0009] Obtain the actual pump speed of the boron diffuser vacuum pump;

[0010] If the absolute value of the deviation between the predicted pump speed and the actual pump speed is greater than the preset pump speed safety deviation, an abnormality warning message will be pushed.

[0011] The correspondence between the attribute data and the pump speed is obtained by: acquiring the process data of the boron expansion equipment in historical records; performing correlation analysis and mechanism analysis on the process data to determine the attribute data affecting the pump speed; and constructing the correspondence between the attribute data and the pump speed.

[0012] In one embodiment, constructing the correspondence between the attribute data and the pump speed includes:

[0013] Smooth the pump speed;

[0014] A training dataset is constructed based on the smoothed pump speed and its corresponding attribute data.

[0015] The random forest algorithm was used to train the training dataset to obtain the pump speed prediction model.

[0016] In one embodiment, the step of performing correlation analysis and mechanism analysis on the process data to determine the attribute data affecting the pump speed includes:

[0017] Based on the process data, a mechanism analysis of the pump speed is performed to determine the initial attribute data affecting the pump speed;

[0018] Analyze the correlation between the initial attribute data and the pump speed;

[0019] Based on the correlation analysis results, attribute data that affects the pump speed are selected from the initial attribute data.

[0020] In one embodiment, obtaining the process data of the boron expansion equipment in historical records includes:

[0021] Obtain the sheet resistance data and initial process data of the boron expansion equipment from historical records;

[0022] The sheet resistance data and the initial process data are matched and fused, and the process data is obtained by filtering from the initial process data.

[0023] In one embodiment, the smoothing of the pump speed includes:

[0024] Perform data cleaning on the pump speed;

[0025] The pump speed after data cleaning is smoothed using a Gaussian algorithm.

[0026] In one embodiment, the step of pushing an abnormality alert message if the absolute value of the deviation between the predicted pump speed and the actual pump speed is greater than a preset pump speed safety deviation includes:

[0027] If the absolute value of the deviation between the predicted pump speed and the actual pump speed is greater than the preset pump speed safety deviation, then the timing will be longer than the cumulative duration.

[0028] If the duration exceeds the preset threshold for consecutive cumulative durations, an error message will be pushed.

[0029] In one embodiment, the attribute data includes gas flow rate, pressure, step sequence, and time consumption.

[0030] Secondly, this application also provides an abnormal early warning device for a boron diffuser vacuum pump. The device includes:

[0031] The data acquisition module is used to acquire real-time attribute data that affects the pump speed during the operation of the boron expansion equipment;

[0032] The prediction module is used to obtain the predicted pump speed of the boron diffuser vacuum pump based on the real-time attribute data and the correspondence between the attribute data and the pump speed.

[0033] Pump speed acquisition module, used to acquire the actual pump speed value of boron diffuser vacuum pump;

[0034] The early warning module is used to push an abnormality warning message when the absolute value of the deviation between the predicted pump speed value and the actual pump speed value is greater than the preset pump speed safety deviation.

[0035] The correspondence between the attribute data and the pump speed is obtained by: acquiring the process data of the boron expansion equipment in historical records; performing correlation analysis and mechanism analysis on the process data to determine the attribute data affecting the pump speed; and constructing the correspondence between the attribute data and the pump speed.

[0036] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0037] Obtain real-time attribute data affecting pump speed during the operation of the boron expansion equipment;

[0038] Based on the real-time attribute data and the correspondence between the attribute data and the pump speed, the predicted pump speed of the boron diffusion vacuum pump is obtained.

[0039] Obtain the actual pump speed of the boron diffuser vacuum pump;

[0040] If the absolute value of the deviation between the predicted pump speed and the actual pump speed is greater than the preset pump speed safety deviation, an abnormality warning message will be pushed.

[0041] The correspondence between the attribute data and the pump speed is obtained by: acquiring the process data of the boron expansion equipment in historical records; performing correlation analysis and mechanism analysis on the process data to determine the attribute data affecting the pump speed; and constructing the correspondence between the attribute data and the pump speed.

[0042] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0043] Obtain real-time attribute data affecting pump speed during the operation of the boron expansion equipment;

[0044] Based on the real-time attribute data and the correspondence between the attribute data and the pump speed, the predicted pump speed of the boron diffusion vacuum pump is obtained.

[0045] Obtain the actual pump speed of the boron diffuser vacuum pump;

[0046] If the absolute value of the deviation between the predicted pump speed and the actual pump speed is greater than the preset pump speed safety deviation, an abnormality warning message will be pushed.

[0047] The correspondence between the attribute data and the pump speed is obtained by: acquiring the process data of the boron expansion equipment in historical records; performing correlation analysis and mechanism analysis on the process data to determine the attribute data affecting the pump speed; and constructing the correspondence between the attribute data and the pump speed.

[0048] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0049] Obtain real-time attribute data affecting pump speed during the operation of the boron expansion equipment;

[0050] Based on the real-time attribute data and the correspondence between the attribute data and the pump speed, the predicted pump speed of the boron diffusion vacuum pump is obtained.

[0051] Obtain the actual pump speed of the boron diffuser vacuum pump;

[0052] If the absolute value of the deviation between the predicted pump speed and the actual pump speed is greater than the preset pump speed safety deviation, an abnormality warning message will be pushed.

[0053] The correspondence between the attribute data and the pump speed is obtained by: acquiring the process data of the boron expansion equipment in historical records; performing correlation analysis and mechanism analysis on the process data to determine the attribute data affecting the pump speed; and constructing the correspondence between the attribute data and the pump speed.

[0054] The aforementioned method, device, computer equipment, storage medium, and computer program product for early warning of abnormalities in boron expansion vacuum pumps acquire real-time attribute data affecting pump speed during the operation of the boron expansion equipment; based on the real-time attribute data and the correspondence between attribute data and pump speed, obtain a predicted pump speed value for the boron expansion vacuum pump; obtain the actual pump speed value for the boron expansion vacuum pump; if the absolute value of the deviation between the predicted pump speed value and the actual pump speed value is greater than the preset safety deviation for pump speed, an abnormality warning message is pushed. In the entire scheme, since the correspondence between attribute data and pump speed is obtained based on correlation analysis and mechanism analysis of historical process data, the corresponding predicted pump speed value can be accurately analyzed based on the real-time acquired attribute data, and then an early warning judgment can be made based on the deviation between the predicted value and the actual value, ultimately achieving accurate early warning of abnormalities in boron expansion vacuum pumps. Attached Figure Description

[0055] Figure 1This is an application environment diagram of the boron diffuser vacuum pump abnormality early warning method in one embodiment;

[0056] Figure 2 This is a flowchart illustrating an abnormal early warning method for a boron diffuser vacuum pump in one embodiment;

[0057] Figure 3 In another embodiment;

[0058] Figure 4 This is a data table that integrates sheet resistance data and process data;

[0059] Figure 5 This is a structural block diagram of a boron vacuum pump abnormality early warning device in one embodiment;

[0060] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0061] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0062] Photovoltaic equipment essentially processes raw silicon wafers to produce finished solar cells. In complete photovoltaic equipment sets, the boron diffusion process completes the boron atom diffusion process on N-type silicon wafers, forming PN junctions. The quality of this process significantly impacts the power generation efficiency of the final solar cells. Practice has shown that the vacuum pump system of the boron diffusion equipment is one of the key components affecting the quality of the processed solar cells. Because the boron diffusion process generates white solid powder, it can clog the vacuum pump and its piping system, leading to uneven gas distribution within the vacuum chamber during the vacuuming process, severely affecting the quality of the processed solar cells. Pump speed is the main parameter for observing whether the vacuum pump system is abnormal. With the development of industrial artificial intelligence, the need for intelligent real-time dynamic anomaly monitoring of components in boron diffusion equipment is becoming increasingly prominent. Effective artificial intelligence algorithms can provide real-time, accurate dynamic monitoring, timely warnings, and loss prevention, greatly improving the yield of processed solar cells and reducing rework rates. Simultaneously, it transforms periodic maintenance into predictive maintenance, improving maintenance efficiency and timeliness. Addressing the above-mentioned needs in traditional technologies, this application provides a boron diffusion vacuum pump anomaly early warning method for photovoltaic manufacturing scenarios.

[0063] Specifically, the boron diffuser vacuum pump anomaly early warning method provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, controller 102 is connected to boron expansion vacuum pump 104, which is a component of the entire boron expansion equipment. The boron expansion equipment operates according to relevant process requirements. Controller 102 acquires historical process data of the boron expansion equipment; performs correlation and mechanism analysis on the process data to determine the attribute data affecting the pump speed; and establishes a correspondence between attribute data and pump speed. When an abnormality warning for the boron expansion vacuum pump is required, controller 102 acquires real-time attribute data affecting the pump speed during the operation of the boron expansion equipment; based on the real-time attribute data and the correspondence between attribute data and pump speed, it acquires the predicted pump speed value of the boron expansion vacuum pump; it acquires the actual pump speed value of the boron expansion vacuum pump; if the absolute value of the deviation between the predicted pump speed value and the actual pump speed value is greater than the preset pump speed safety deviation, an abnormality warning message is pushed. Furthermore, this abnormality warning message can be directly pushed to the central control platform so that management personnel are aware of the current abnormality of the boron expansion vacuum pump. Specifically, the abnormality warning message is pushed to management personnel in a visual display manner.

[0064] In one embodiment, such as Figure 2 As shown, a method for early warning of abnormalities in a boron diffuser vacuum pump is provided, which is then applied to... Figure 1 Taking controller 102 as an example, the following steps are included:

[0065] S200: Acquire real-time attribute data that affects pump speed during the operation of the boron expansion equipment.

[0066] In actual operation, various parameters affect the pump speed of boron expansion equipment. Specifically, historical process data of the boron expansion equipment can be analyzed for mechanisms and correlations to identify the attribute data affecting the pump speed. Real-time attribute data can be directly obtained when an abnormality warning for the boron expansion vacuum pump is needed.

[0067] S400: Based on real-time attribute data and the correspondence between attribute data and pump speed, obtain the predicted pump speed value of the boron diffusion vacuum pump.

[0068] The correspondence between attribute data and pump speed is a pre-built correspondence. Specifically, it can be obtained by analyzing historical data to obtain attribute data that affects pump speed, and then constructing the correspondence between these attribute data and pump speed.

[0069] Specifically, the correspondence between attribute data and pump speed is obtained as follows: acquiring historical process data of the boron expansion equipment; performing correlation and mechanistic analysis on the process data to determine the attribute data affecting pump speed; and constructing the correspondence between attribute data and pump speed. In practical applications, acquiring historical process data of the boron expansion equipment involves: first, collecting process data generated during the past operation of the boron expansion equipment. This data should include various attributes and parameters of the equipment, such as gas flow rate, pressure, sequence, and time consumption. Performing correlation and mechanistic analysis on the process data involves using statistical methods to conduct in-depth analysis of the collected data. Correlation analysis can determine the degree of association between different attributes, while mechanistic analysis, based on physical and chemical principles, delves into the intrinsic relationships between attributes. Determining attribute data affecting pump speed involves identifying which attribute data are significantly correlated with pump speed. These attribute data may directly affect pump speed or may affect pump speed through interactions with other attributes. Constructing the correspondence between attribute data and pump speed: Based on the results of correlation analysis and mechanism analysis, construct a mathematical model or algorithm to describe the correspondence between attribute data and pump speed. This can be a trained machine learning model.

[0070] S600: Obtain the actual pump speed of the boron diffuser vacuum pump.

[0071] Specifically, the actual pump speed of the boron diffuser vacuum pump can be obtained through sensors.

[0072] S800: If the absolute value of the deviation between the predicted pump speed and the actual pump speed is greater than the preset pump speed safety deviation, an abnormality warning message will be pushed.

[0073] Calculate the absolute value of the deviation between the predicted pump speed and the actual pump speed. If the absolute value of the deviation is greater than the preset safety deviation for the pump speed, it indicates that the current boron diffuser vacuum pump is experiencing an abnormality, and an abnormality alert message will be pushed out. If not necessary, this abnormality alert message can be pushed out visually to allow management personnel to understand the current abnormality in a timely and accurate manner.

[0074] The aforementioned method for early warning of abnormalities in boron expansion vacuum pumps involves acquiring real-time attribute data affecting pump speed during the operation of the boron expansion equipment; obtaining a predicted pump speed value based on the real-time attribute data and the correspondence between the attribute data and pump speed; obtaining the actual pump speed value; and pushing an abnormality warning message if the absolute value of the deviation between the predicted and actual pump speed values ​​exceeds a preset safety deviation. In this entire scheme, since the correspondence between attribute data and pump speed is obtained through correlation and mechanism analysis based on historical process data, the corresponding predicted pump speed value can be accurately obtained based on the real-time acquired attribute data. Furthermore, an early warning judgment is made based on the deviation between the predicted and actual values, ultimately achieving accurate early warning of abnormalities in the boron expansion vacuum pump.

[0075] In one embodiment, constructing the correspondence between attribute data and pump speed includes:

[0076] The pump speed is smoothed; a training dataset is constructed based on the smoothed pump speed and its corresponding attribute data; the random forest algorithm is used to train the training dataset to obtain a pump speed prediction model.

[0077] In this embodiment, a pump speed prediction model is used to represent the correspondence between attribute data and pump speed. The input to the pump speed prediction model is the attribute data, and the output is the pump speed. Constructing the correspondence between attribute data and pump speed can be simply understood as the process of training the pump speed prediction model. Specifically, during the training process, the pump speed is first smoothed. The smoothed pump speed is used as the model output, and the corresponding attribute data is used as the model input to construct a training dataset. A random forest algorithm is then used to train the training dataset to obtain the pump speed prediction model. In other words, the initial random forest model is trained based on the training dataset to obtain a final pump speed prediction model that accurately represents the correspondence between attribute data and pump speed.

[0078] In one embodiment, correlation analysis and mechanism analysis are performed on the process data to determine the attribute data affecting the pump speed, including:

[0079] Mechanism analysis of pump speed is performed based on process data to determine the initial attribute data affecting pump speed; the correlation between the initial attribute data and pump speed is analyzed; based on the correlation analysis results, attribute data affecting pump speed are selected from the initial attribute data.

[0080] Mechanism Analysis: The pump speed is adjusted using PID control based on the setpoint and actual pressure within the pipe cavity; therefore, pressure is used as the output parameter. The pressure PID control formula is as follows:

[0081] P(t)=Kp*e(t)+Ki*∫e(t)dt+Kd*de(t) / dt;

[0082] Where P(t) is the output pressure value; e(t) is the current error value; Kp, Ki, and Kd are the proportional, integral, and derivative parameters, respectively; ∫e(t)dt is the integral value of the error; and de(t) / dt is the derivative value of the error. The main factor affecting pressure is the gas flow rate, therefore, the gas flow rate is used as an input parameter. Since the pump speed varies depending on the setpoint of each step parameter, the step sequence is also used as an input parameter. The pump speed exhibits regular nonlinear changes over time during the control process, therefore, the time consumption is included as a time-series characteristic in the input parameters. Specifically, the gas flow rate includes six types of gas flow rates: BO2 (large oxygen), SO2 (small oxygen), SN2 (small nitrogen), DN2 (large nitrogen), PN2 (furnace door nitrogen), and BCL3 (boron trichloride).

[0083] Correlation analysis: The correlation coefficient between each parameter and the pump speed can be calculated using the following formula:

[0084]

[0085] Where r is the correlation coefficient, -1 ≤ r ≤ 1, xi is the input parameter value, and yi is the output parameter value. It is not strictly necessary; after performing correlation analysis, the conclusions of the mechanism analysis can be verified through a correlation matrix plot.

[0086] like Figure 3 As shown, in one embodiment, S200 includes:

[0087] S220: Obtain sheet resistance data and initial process data of the boron expansion equipment from historical records;

[0088] S240: Match and merge the sheet resistance data and the initial process data, and filter out the process data from the initial process data.

[0089] Here, the acquired initial process data is matched and fused with sheet resistance data to filter out accurate and effective process data. Specifically, sheet resistance data and process data can be matched and fused based on time, furnace number, tube number, and boat number, and some feature parameters of each set of process data can be extracted. Further, the obtained pump speeds can be cleaned to remove null values ​​and outliers, and then smoothed using a Gaussian algorithm. In practical applications, smoothing specifically refers to Gaussian smoothing, which takes the pump speed point value x as input and outputs G(x) with the pump speed weights. The specific formula is as follows:

[0090]

[0091] Multiplying G(x) by the point value of the pump speed x yields the smoothed pump speed value. The processed data format is as follows: Figure 4 As shown.

[0092] In one embodiment, if the absolute value of the deviation between the predicted pump speed and the actual pump speed is greater than a preset safe deviation for pump speed, an abnormality alert message is pushed, including:

[0093] If the absolute value of the deviation between the predicted pump speed and the actual pump speed is greater than the preset pump speed safety deviation, the timer will continuously exceed the cumulative duration; if the timer continuously exceeds the cumulative duration and is greater than the preset duration threshold, an abnormality alert message will be pushed.

[0094] The preset duration threshold is a pre-defined time limit that can be adjusted according to actual needs, such as 30 seconds or 60 seconds. When the absolute value of the deviation between the predicted pump speed and the actual pump speed is detected to be greater than the preset safe deviation, the system will continuously exceed the cumulative duration. If the cumulative duration exceeds the preset duration threshold, it indicates that the boron diffusion vacuum pump has malfunctioned, and an abnormality alert message is pushed. In this embodiment, the abnormality alert message is only pushed after the absolute value of the deviation between the predicted pump speed and the actual pump speed has been greater than the preset safe deviation for a certain period (the preset duration threshold) to avoid frequent false alarms and improve the accuracy of early warning.

[0095] In practical applications, the predicted pump speed value Vi is obtained in real time based on the real-time collected input parameters and the prediction model. At the same time, the actual pump speed value Xi is collected in real time, and a safety deviation δ for the pump speed value is set. If |Vi-Xi|>δ and continues for more than 1 minute, the pump speed is judged to be abnormal, and then the vacuum pump system is judged to be abnormal. The abnormal information is saved in the database and pushed to the main page and the abnormal warning query list. It is also pushed to the process engineer for inspection and maintenance, realizing real-time dynamic early warning of the pump.

[0096] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0097] Based on the same inventive concept, this application also provides a boron diffusion vacuum pump anomaly early warning device for implementing the aforementioned boron diffusion vacuum pump anomaly early warning method. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations of one or more boron diffusion vacuum pump anomaly early warning device embodiments provided below can be found in the limitations of the boron diffusion vacuum pump anomaly early warning method described above, and will not be repeated here.

[0098] In one embodiment, such as Figure 5 As shown, a boron diffuser vacuum pump abnormality early warning device is provided, comprising:

[0099] The data acquisition module 200 is used to acquire real-time attribute data that affects the pump speed during the operation of the boron expansion equipment;

[0100] The prediction module 400 is used to obtain the predicted pump speed of the boron diffuser vacuum pump based on real-time attribute data and the correspondence between attribute data and pump speed.

[0101] Pump speed acquisition module 600 is used to acquire the actual pump speed value of the boron diffuser vacuum pump;

[0102] The early warning module 800 is used to push an abnormality warning message when the absolute value of the deviation between the predicted pump speed and the actual pump speed is greater than the preset pump speed safety deviation.

[0103] The correspondence between attribute data and pump speed is obtained in the following way: acquiring the process data of the boron expansion equipment in historical records; performing correlation analysis and mechanism analysis on the process data to determine the attribute data affecting the pump speed; and constructing the correspondence between attribute data and pump speed.

[0104] In one embodiment, the above-mentioned boron-expanding vacuum pump abnormality early warning device further includes a model training module for smoothing the pump speed; constructing a training dataset based on the smoothed pump speed and corresponding attribute data; and training the training dataset using a random forest algorithm to obtain a pump speed prediction model.

[0105] In one embodiment, the model training module is further configured to perform mechanistic analysis on pump speed based on process data, determine initial attribute data affecting pump speed, analyze the correlation between initial attribute data and pump speed, and select attribute data affecting pump speed from the initial attribute data based on the correlation analysis results.

[0106] In one embodiment, the data acquisition module 200 is further configured to acquire sheet resistance data and initial process data of the boron expansion equipment in historical records; match and fuse the sheet resistance data and the initial process data, and filter out process data from the initial process data.

[0107] In one embodiment, the model training module is also used to perform data cleaning on the pump speed; and to smooth the pump speed after data cleaning using a Gaussian algorithm.

[0108] In one embodiment, the early warning module 800 is further configured to, when the absolute value of the deviation between the predicted pump speed value and the actual pump speed value is greater than the preset pump speed safety deviation, keep the timer for a continuous period of time greater than the cumulative duration; if the continuous period of time greater than the cumulative duration is greater than the preset duration threshold, then push an abnormal prompt message.

[0109] In one embodiment, the attribute data includes gas flow rate, pressure, step sequence, and time.

[0110] Each module in the aforementioned boron diffuser vacuum pump abnormality early warning device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0111] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 6 As shown, the computer device includes a processor, memory, communication interface, display screen, and input device connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for early warning of abnormalities in a boron diffusion vacuum pump.

[0112] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0113] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0114] Obtain real-time attribute data affecting pump speed during the operation of the boron expansion equipment;

[0115] Based on real-time attribute data and the correspondence between attribute data and pump speed, the predicted pump speed of the boron diffuser vacuum pump is obtained.

[0116] Obtain the actual pump speed of the boron diffuser vacuum pump;

[0117] If the absolute value of the deviation between the predicted pump speed and the actual pump speed is greater than the preset safe deviation of the pump speed, an abnormality warning message will be pushed.

[0118] The correspondence between attribute data and pump speed is obtained in the following way: acquiring the process data of the boron expansion equipment in historical records; performing correlation analysis and mechanism analysis on the process data to determine the attribute data affecting the pump speed; and constructing the correspondence between attribute data and pump speed.

[0119] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0120] The pump speed is smoothed; a training dataset is constructed based on the smoothed pump speed and its corresponding attribute data; the random forest algorithm is used to train the training dataset to obtain a pump speed prediction model.

[0121] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0122] Mechanism analysis of pump speed is performed based on process data to determine the initial attribute data affecting pump speed; the correlation between the initial attribute data and pump speed is analyzed; based on the correlation analysis results, attribute data affecting pump speed are selected from the initial attribute data.

[0123] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0124] Obtain sheet resistance data and initial process data of the boron expansion equipment from historical records; match and merge the sheet resistance data and initial process data, and filter out the process data from the initial process data.

[0125] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0126] The pump speed data is cleaned; the cleaned pump speed data is then smoothed using a Gaussian algorithm.

[0127] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0128] If the absolute value of the deviation between the predicted pump speed and the actual pump speed is greater than the preset pump speed safety deviation, the timer will continuously exceed the cumulative duration; if the timer continuously exceeds the cumulative duration and is greater than the preset duration threshold, an abnormality alert message will be pushed.

[0129] In one embodiment, the attribute data includes gas flow rate, pressure, step sequence, and time.

[0130] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0131] Obtain real-time attribute data affecting pump speed during the operation of the boron expansion equipment;

[0132] Based on real-time attribute data and the correspondence between attribute data and pump speed, the predicted pump speed of the boron diffuser vacuum pump is obtained.

[0133] Obtain the actual pump speed of the boron diffuser vacuum pump;

[0134] If the absolute value of the deviation between the predicted pump speed and the actual pump speed is greater than the preset safe deviation of the pump speed, an abnormality warning message will be pushed.

[0135] The correspondence between attribute data and pump speed is obtained in the following way: acquiring the process data of the boron expansion equipment in historical records; performing correlation analysis and mechanism analysis on the process data to determine the attribute data affecting the pump speed; and constructing the correspondence between attribute data and pump speed.

[0136] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0137] The pump speed is smoothed; a training dataset is constructed based on the smoothed pump speed and its corresponding attribute data; the random forest algorithm is used to train the training dataset to obtain a pump speed prediction model.

[0138] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0139] Mechanism analysis of pump speed is performed based on process data to determine the initial attribute data affecting pump speed; the correlation between the initial attribute data and pump speed is analyzed; based on the correlation analysis results, attribute data affecting pump speed are selected from the initial attribute data.

[0140] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0141] Obtain sheet resistance data and initial process data of the boron expansion equipment from historical records; match and merge the sheet resistance data and initial process data, and filter out the process data from the initial process data.

[0142] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0143] The pump speed data is cleaned; the cleaned pump speed data is then smoothed using a Gaussian algorithm.

[0144] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0145] If the absolute value of the deviation between the predicted pump speed and the actual pump speed is greater than the preset pump speed safety deviation, the timer will continuously exceed the cumulative duration; if the timer continuously exceeds the cumulative duration and is greater than the preset duration threshold, an abnormality alert message will be pushed.

[0146] In one embodiment, the attribute data includes gas flow rate, pressure, step sequence, and time.

[0147] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0148] Obtain real-time attribute data affecting pump speed during the operation of the boron expansion equipment;

[0149] Based on real-time attribute data and the correspondence between attribute data and pump speed, the predicted pump speed of the boron diffuser vacuum pump is obtained.

[0150] Obtain the actual pump speed of the boron diffuser vacuum pump;

[0151] If the absolute value of the deviation between the predicted pump speed and the actual pump speed is greater than the preset safe deviation of the pump speed, an abnormality warning message will be pushed.

[0152] The correspondence between attribute data and pump speed is obtained in the following way: acquiring the process data of the boron expansion equipment in historical records; performing correlation analysis and mechanism analysis on the process data to determine the attribute data affecting the pump speed; and constructing the correspondence between attribute data and pump speed.

[0153] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0154] The pump speed is smoothed; a training dataset is constructed based on the smoothed pump speed and its corresponding attribute data; the random forest algorithm is used to train the training dataset to obtain a pump speed prediction model.

[0155] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0156] Mechanism analysis of pump speed is performed based on process data to determine the initial attribute data affecting pump speed; the correlation between the initial attribute data and pump speed is analyzed; based on the correlation analysis results, attribute data affecting pump speed are selected from the initial attribute data.

[0157] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0158] Obtain sheet resistance data and initial process data of the boron expansion equipment from historical records; match and merge the sheet resistance data and initial process data, and filter out the process data from the initial process data.

[0159] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0160] The pump speed data is cleaned; the cleaned pump speed data is then smoothed using a Gaussian algorithm.

[0161] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0162] If the absolute value of the deviation between the predicted pump speed and the actual pump speed is greater than the preset pump speed safety deviation, the timer will continuously exceed the cumulative duration; if the timer continuously exceeds the cumulative duration and is greater than the preset duration threshold, an abnormality alert message will be pushed.

[0163] In one embodiment, the attribute data includes gas flow rate, pressure, step sequence, and time.

[0164] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0165] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0166] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0167] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for early warning of abnormalities in a boron diffuser vacuum pump, characterized in that, The method includes: Obtain real-time attribute data affecting pump speed during the operation of the boron expansion equipment; Based on the real-time attribute data and the correspondence between the attribute data and the pump speed, the predicted pump speed of the boron diffusion vacuum pump is obtained. Obtain the actual pump speed of the boron diffuser vacuum pump; If the absolute value of the deviation between the predicted pump speed and the actual pump speed is greater than the preset pump speed safety deviation, an abnormality warning message will be pushed. The correspondence between the attribute data and the pump speed is obtained by: acquiring the process data of the boron expansion equipment in historical records; performing correlation analysis and mechanism analysis on the process data to determine the attribute data affecting the pump speed; and constructing the correspondence between the attribute data and the pump speed.

2. The method according to claim 1, characterized in that, The process of constructing the correspondence between the attribute data and the pump speed includes: Smooth the pump speed; A training dataset is constructed based on the smoothed pump speed and its corresponding attribute data. The random forest algorithm was used to train the training dataset to obtain the pump speed prediction model.

3. The method according to claim 1, characterized in that, The correlation and mechanism analysis performed on the process data to determine the attribute data affecting the pump speed includes: Based on the process data, a mechanism analysis of the pump speed is performed to determine the initial attribute data affecting the pump speed; Analyze the correlation between the initial attribute data and the pump speed; Based on the correlation analysis results, attribute data that affects the pump speed are selected from the initial attribute data.

4. The method according to claim 1, characterized in that, The process data of the boron expansion equipment obtained from historical records includes: Obtain the sheet resistance data and initial process data of the boron expansion equipment from historical records; The sheet resistance data and the initial process data are matched and fused, and the process data is obtained by filtering from the initial process data.

5. The method according to claim 2, characterized in that, The pump speed smoothing process includes: Perform data cleaning on the pump speed; The pump speed after data cleaning is smoothed using a Gaussian algorithm.

6. The method according to claim 1, characterized in that, If the absolute value of the deviation between the predicted pump speed and the actual pump speed is greater than the preset pump speed safety deviation, the abnormality alert message pushed includes: If the absolute value of the deviation between the predicted pump speed and the actual pump speed is greater than the preset pump speed safety deviation, then the timing will be longer than the cumulative duration. If the duration exceeds the preset threshold for consecutive cumulative durations, an error message will be pushed.

7. The method according to claim 1, characterized in that, The attribute data includes gas flow rate, pressure, step sequence, and time consumption.

8. An abnormal early warning device for a boron diffuser vacuum pump, characterized in that, The device includes: The data acquisition module is used to acquire real-time attribute data that affects the pump speed during the operation of the boron expansion equipment; The prediction module is used to obtain the predicted pump speed of the boron diffuser vacuum pump based on the real-time attribute data and the correspondence between the attribute data and the pump speed. Pump speed acquisition module, used to acquire the actual pump speed value of boron diffuser vacuum pump; The early warning module is used to push an abnormality warning message when the absolute value of the deviation between the predicted pump speed value and the actual pump speed value is greater than the preset pump speed safety deviation. The correspondence between the attribute data and the pump speed is obtained by: acquiring the process data of the boron expansion equipment in historical records; performing correlation analysis and mechanism analysis on the process data to determine the attribute data affecting the pump speed; and constructing the correspondence between the attribute data and the pump speed.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements 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 computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images