Intelligent hibernation wakeup method and device based on active prediction, equipment and medium

Abstract

The application relates to the technical field of semiconductor manufacturing equipment control, and specifically provides an intelligent hibernation wake-up method and device based on active prediction, equipment and a medium. The method comprises the following steps: acquiring an estimated execution time node and process parameter information of a next process task to be executed by a current thermal annealing equipment, and acquiring a maximum wake-up time consumption of the current thermal annealing equipment; the maximum wake-up time consumption is the maximum value of preset wake-up time consumptions corresponding to systems in the thermal annealing equipment; a safe wake-up time node is calculated according to the estimated execution time node and the maximum wake-up time consumption; when the difference between a current time node and the safe wake-up time node is greater than a preset threshold, the systems in the thermal annealing equipment are adjusted from a running state to a hibernation state; when the current time node reaches the safe wake-up time node, the systems in the thermal annealing equipment are adjusted from the hibernation state to a process ready state according to the process parameter information; and the method can significantly reduce the standby energy consumption of the thermal annealing equipment and improve the energy utilization efficiency.

Description

Technical Field

[0001] This application relates to the field of semiconductor manufacturing equipment control technology, and more specifically, to a method, apparatus, device, and medium for intelligent sleep / wake-up based on active prediction. Background Technology

[0002] In semiconductor manufacturing processes, thermal annealing equipment, as a critical process tool, is facing increasingly prominent energy consumption issues. Traditional thermal annealing equipment typically operates in a continuous standby mode to ensure process stability, resulting in significant energy waste. Specifically: the heating system needs to maintain a base temperature for extended periods to prevent thermal shock, leading to substantial radiative and convective heat loss; the vacuum system operates continuously to avoid the time-consuming process of re-vacuuming, consuming large amounts of electricity; and various auxiliary subsystems, such as process gas delivery systems and cooling water circulation systems, run idle for extended periods. This unnecessary energy consumption not only increases production costs but also contradicts the current trend of green manufacturing.

[0003] More importantly, existing technologies cannot achieve precise matching between equipment operating status and process requirements. Due to the lack of intelligent prediction of equipment wake-up time and precise control of state transitions, equipment often enters the ready state prematurely or maintains high-power operation when not needed. This extensive control method not only wastes energy but also affects the service life of critical equipment components. Especially in multi-task intermittent production scenarios, traditional control methods struggle to dynamically adjust equipment status according to the time nodes of process tasks, causing equipment to continuously consume energy during waiting periods.

[0004] There is currently no effective technical solution to the above problems. Summary of the Invention

[0005] The purpose of this application is to provide a method, device, equipment and medium for intelligent sleep-wake based on active prediction, which can significantly reduce the standby power consumption of thermal annealing equipment and improve energy utilization efficiency.

[0006] In a first aspect, this application provides an intelligent sleep / wake-up method based on active prediction, applied in a thermal annealing device, which includes the following steps:

[0007] S1. Obtain the estimated execution time node and process parameter information of the next process task to be executed by the current hot annealing equipment, and obtain the maximum wake-up time of the current hot annealing equipment; the maximum wake-up time is the maximum value of the preset wake-up time corresponding to each system in the hot annealing equipment;

[0008] S2. Calculate the safe wake-up time node based on the expected execution time node and the maximum wake-up time;

[0009] S3. When the difference between the current time node and the safe wake-up time node is greater than the preset threshold, adjust each system in the thermal annealing equipment from the running state to the sleep state.

[0010] S4. When the safe wake-up time node is reached at the current time node, adjust each system in the hot annealing equipment from the dormant state to the process ready state according to the process parameter information; for each system in the hot annealing equipment, the operating power of the system in the dormant state is less than its operating power in the process ready state, and the operating parameters of the system in the process ready state are the process parameter information.

[0011] This application provides an intelligent sleep / wake-up method based on proactive prediction. By introducing the concepts of expected execution time node, maximum wake-up time, and safe wake-up time node, and combining them with a dynamic power consumption management strategy, it realizes intelligent switching of device state. This method avoids unnecessary energy consumption when the device is idle for a long time, while ensuring that the device can enter the process-ready state on time and accurately when needed, thereby significantly reducing the standby power consumption of the device and improving energy utilization efficiency.

[0012] Optionally, step S1 includes:

[0013] S11. Obtain the estimated execution time node and process parameter information of the next process task to be executed in the current hot annealing equipment, and obtain the preset wake-up time corresponding to each system in the hot annealing equipment;

[0014] S12. Obtain environmental parameter information;

[0015] S13. For each system in the hot annealing equipment, obtain the cumulative runtime, historical operating parameters and historical maintenance information of that system;

[0016] S14. For each system in the hot annealing equipment, based on environmental parameter information and the system's corresponding cumulative runtime, historical operating parameters and historical maintenance information, the preset wake-up time of the system is corrected to obtain the corrected wake-up time of the system.

[0017] S15. Use the maximum value among all corrected wake-up times as the maximum wake-up time for the current thermal annealing device.

[0018] Optionally, step S2 includes:

[0019] S21. Obtain historical execution time fluctuation data of the current hot annealing equipment; the historical execution time fluctuation data includes the difference between at least one historical estimated execution time and the historical actual execution time.

[0020] S22. Determine the buffer time based on historical execution time fluctuation data;

[0021] S23. Calculate the safe wake-up time node based on the expected execution time node, buffer time, and maximum wake-up time.

[0022] Optionally, step S23 includes:

[0023] S231. Obtain the operating status information of upstream equipment and the emergency order information of the production line where the current hot annealing equipment is located;

[0024] S232. Adjust the buffer time based on the operating status information and emergency order information;

[0025] S233. Analyze whether the adjusted buffer time is within the preset time range. If yes, then take the adjusted buffer time as the final buffer time. If no, then proceed to step S234.

[0026] S234. When the buffer time is greater than the upper limit of the preset time range, the upper limit of the preset time range shall be used as the final buffer time; when the buffer time is less than the lower limit of the preset time range, the lower limit of the preset time range shall be used as the final buffer time.

[0027] S235. Calculate the safe wake-up time node based on the expected execution time node, buffer time, and maximum wake-up time.

[0028] Optionally, step S3 includes:

[0029] S31. When the difference between the current time node and the safe wake-up time node is greater than the preset threshold, record the state compensation parameters corresponding to each system in the current hot annealing equipment, and then adjust each system in the hot annealing equipment from the running state to the sleep state.

[0030] Step S4 includes:

[0031] S41. When the safe wake-up time node is reached at the current time node, adjust each system in the hot annealing equipment from the dormant state to the process ready state according to the process parameter information, and calibrate each system in the hot annealing equipment according to the state compensation parameters during the adjustment process.

[0032] Optionally, the thermal annealing equipment includes an electric heating element and a vacuum gauge. The state compensation parameters include the resistance and temperature variation curves of the electric heating element and the zero-point offset background value of the vacuum gauge. The process of calibrating each system in the thermal annealing equipment according to the state compensation parameters includes:

[0033] A1. Obtain the real-time temperature and resistance value of the electric heating component;

[0034] A2. Extract the corresponding temperature from the curve of resistance and temperature change based on the real-time resistance value as the reference temperature;

[0035] A3. Based on the deviation between the reference temperature and the real-time temperature, obtain the resistance and temperature change curves to obtain the resistance and temperature correction curves, and then control the temperature of the electric heating component based on the resistance and temperature correction curves.

[0036] A4. Obtain the real-time zero point value of the vacuum gauge;

[0037] A5. The vacuum level measured by the vacuum gauge is calibrated based on the deviation between the real-time zero point value and the zero point offset background value.

[0038] Optionally, the intelligent sleep / wake method based on proactive prediction further includes the following steps:

[0039] B1. When adjusting each system in the hot annealing equipment from a dormant state to a process-ready state and an upstream equipment failure occurs, acquire upstream equipment failure parameter information and upstream equipment process progress information; the failure parameter information includes the failure type and failure severity.

[0040] B2. Based on the fault parameter information and the upstream equipment process progress information, generate the predicted execution time node for the next process task to be executed by the current hot annealing equipment;

[0041] B3. Analyze whether the deviation between the predicted execution time node and the expected execution time node is greater than the preset time threshold. If yes, proceed to step B4. If no, continue to adjust each system in the hot annealing equipment from the dormant state to the process ready state according to the process parameter information, and return to step B1.

[0042] B4. Recalculate the safe wake-up time node based on the predicted execution time node and the maximum wake-up time, and adjust each system in the hot annealing equipment to the intermediate maintenance state; for each system in the hot annealing equipment, the operating power of the system in the intermediate maintenance state is less than its operating power in the process ready state and greater than its operating power in the dormant state.

[0043] B5. When the recalculated safe wake-up time point is reached at the current time point, adjust each system in the hot annealing equipment from the intermediate maintenance state to the process ready state according to the process parameter information.

[0044] Secondly, this application also provides an intelligent sleep / wake-up device based on active prediction, applied in a thermal annealing apparatus, comprising:

[0045] The parameter acquisition module is used to obtain the estimated execution time node and process parameter information of the next process task to be executed by the current hot annealing equipment, and to obtain the maximum wake-up time of the current hot annealing equipment; the maximum wake-up time is the maximum value of the preset wake-up time corresponding to each system in the hot annealing equipment;

[0046] The node calculation module is used to calculate the safe wake-up time node based on the expected execution time node and the maximum wake-up time.

[0047] The hibernation switching module is used to switch each system in the thermal annealing equipment from running state to hibernation state when the difference between the current time node and the safe wake-up time node is greater than a preset threshold.

[0048] The wake-up switching module is used to adjust each system in the hot annealing equipment from the dormant state to the process-ready state according to the process parameter information when the safe wake-up time node is reached at the current time node. For each system in the hot annealing equipment, the operating power of the system in the dormant state is less than its operating power in the process-ready state, and the operating parameters of the system in the process-ready state are the process parameter information.

[0049] This application provides an intelligent sleep / wake-up device based on active prediction. By introducing the concepts of expected execution time node, maximum wake-up time, and safe wake-up time node, and combining them with a dynamic power consumption management strategy, it realizes intelligent switching of device state. This method avoids unnecessary energy consumption when the device is idle for a long time, while ensuring that the device can enter the process-ready state on time and accurately when needed, thereby significantly reducing the standby power consumption of the device and improving energy utilization efficiency.

[0050] Thirdly, this application provides an electronic device including a processor and a memory, the memory storing computer-readable instructions, which, when executed by the processor, perform the steps of the method provided in the first aspect above.

[0051] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the steps of the method provided in the first aspect above.

[0052] As can be seen from the above, the intelligent sleep-wake method, device, equipment and medium based on active prediction provided in this application, by introducing the concepts of expected execution time node, maximum wake-up time and safe wake-up time node, and combining them with dynamic power consumption management strategy, realizes intelligent switching of device state. This method avoids unnecessary energy consumption when the device is idle for a long time, while ensuring that the device can enter the process-ready state on time and accurately when needed, thereby significantly reducing the standby power consumption of the device and improving energy utilization efficiency. Attached Figure Description

[0053] Figure 1 A flowchart of an intelligent sleep-wake method based on active prediction provided in an embodiment of this application.

[0054] Figure 2This is a schematic diagram of the structure of an intelligent sleep / wake-up device based on active prediction, provided in an embodiment of this application.

[0055] Figure 3 This is a schematic diagram of an electronic device structure provided in an embodiment of this application.

[0056] Reference numerals: 1. Parameter acquisition module; 2. Node calculation module; 3. Sleep switching module; 4. Wake-up switching module; 101. Processor; 102. Memory; 103. Communication bus. Detailed Implementation

[0057] 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. The components of the embodiments of this application described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0058] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0059] Firstly, such as Figure 1 As shown, this application provides an intelligent sleep / wake-up method based on active prediction, which includes the following steps:

[0060] S1. Obtain the estimated execution time node and process parameter information of the next process task to be executed by the current hot annealing equipment, and obtain the maximum wake-up time of the current hot annealing equipment; the maximum wake-up time is the maximum value of the preset wake-up time corresponding to each system in the hot annealing equipment;

[0061] S2. Calculate the safe wake-up time node based on the expected execution time node and the maximum wake-up time;

[0062] S3. When the difference between the current time node and the safe wake-up time node is greater than the preset threshold, adjust each system in the thermal annealing equipment from the running state to the sleep state.

[0063] S4. When the safe wake-up time node is reached at the current time node, adjust each system in the hot annealing equipment from the dormant state to the process ready state according to the process parameter information; for each system in the hot annealing equipment, the operating power of the system in the dormant state is less than its operating power in the process ready state, and the operating parameters of the system in the process ready state are the process parameter information.

[0064] For ease of understanding, some key terms in this embodiment are explained below. The estimated execution time node in this embodiment refers to the planned start time of the next process task to be performed by the heat annealing equipment. This time node is typically calculated by the Manufacturing Execution System (MES) or Advanced Planning and Scheduling System (APS) based on factors such as production plan, material availability, and equipment status. It should be understood that the calculation of the estimated execution time node is prior art, and its calculation process will not be discussed in detail here. The process parameter information in this embodiment refers to all operating parameters required for the next process task to be performed by the heat annealing equipment, such as temperature profile, gas flow rate, pressure, and processing time. These parameters are crucial for ensuring product quality and process repeatability. The maximum wake-up time in this embodiment refers to the maximum time (preset wake-up time) required for all subsystems in the thermal annealing equipment to recover from a dormant state to a process-ready state. For example, if the heating system requires 30 seconds to wake up and the vacuum system requires 25 seconds, the maximum wake-up time is 30 seconds. This parameter is crucial to ensuring that the equipment is fully ready before the expected execution time. The preset wake-up time in this embodiment is preferably obtained by measuring the thermal annealing equipment through multiple wake-up experiments (experiments that restore the thermal annealing equipment from a dormant state to a process-ready state). The safe wake-up time in this embodiment refers to the point in time when the thermal annealing equipment must begin to wake up from a dormant state to ensure that it is fully ready for process execution by the expected execution time. This time can be calculated by subtracting the maximum wake-up time from the expected execution time. The dormant state in this embodiment refers to a low-power operating mode of the thermal annealing equipment during non-production periods. In this state, the operating power of the equipment is significantly lower than that in the process-ready state, but some functions are still maintained to achieve rapid wake-up. For example, the lamp heating system may be maintained at a lower safe storage temperature (e.g., the temperature of the lamp heating system in the process-ready state is 650°C, while the temperature in the dormant state is 50°C), and the vacuum system may only rely on the chamber vacuum holding valve to maintain the vacuum level. The process-ready state in this embodiment refers to the state in which the thermal annealing equipment is fully ready to perform process tasks. In this state, all operating parameters of the equipment (such as temperature, vacuum level, gas flow rate, etc.) have reached the target values ​​set by the process parameter information, and wafer processing can begin at any time.

[0065] This application proposes an intelligent sleep / wake-up method based on proactive prediction. By dynamically scheduling device states, the device enters a low-power sleep state when idle and is precisely woken up before the start of a process task, thereby reducing energy consumption during non-production periods. In specific implementation, the method includes the following steps:

[0066] In step S1, the system obtains the estimated execution time and process parameter information of the next process task to be executed by the current thermal annealing equipment, and obtains the maximum wake-up time of the current thermal annealing equipment. Specifically, the equipment control system can obtain the production schedule in real time from the Manufacturing Execution System (MES) or Advanced Planning and Scheduling System (APS) through standard interfaces (such as SECS / GEM, OPCUA), and parse the estimated arrival time and process parameters of the next batch of wafers from the production schedule (this parsing is prior art). Then, the parsed estimated arrival time of the next batch of wafers is used as the estimated execution time of the next process task to be executed by the current thermal annealing equipment, and the parsed process parameters are used as the process parameter information of the next process task to be executed by the current thermal annealing equipment. To obtain the maximum wake-up time, each subsystem in the thermal annealing equipment can be tested in advance, and the time required for each subsystem to recover from the dormant state to the process-ready state can be recorded. Then, the maximum value among all subsystems can be taken as the maximum wake-up time. For example, through multiple tests, the longest time for the lamp heating system to rise from the storage temperature to the preheating temperature is 30 seconds, and the longest time for the vacuum system to recover from the vacuum state to the vacuum level required by the process is 25 seconds. Therefore, the maximum wake-up time is determined to be 30 seconds.

[0067] In step S2, the system calculates the safe wake-up time node based on the expected execution time node and the maximum wake-up time. The safe wake-up time node is calculated by subtracting the maximum wake-up time from the expected execution time node. For example, if the expected execution time node of the next process task is 10:00 AM and the maximum wake-up time is 30 seconds, the safe wake-up time node will be calculated as 9:59:30 AM. This calculation ensures that the equipment has sufficient time to fully recover from hibernation and reach the process-ready state when the process starts.

[0068] In step S3, when the difference between the current time node and the safe wake-up time node is greater than a preset threshold, the system adjusts each system in the thermal annealing equipment from the running state to the sleep state. When the system detects that the difference between the current time node and the safe wake-up time node exceeds the preset threshold, it indicates that the equipment will have a long idle time. At this time, the system will trigger the equipment to enter the sleep state. For example, the preset threshold can be set to 15 minutes. If the difference between the current time node and the safe wake-up time node exceeds 15 minutes, the lamp heating system can lower the temperature to a lower safe storage temperature (e.g., 50-80℃). This safe storage temperature is lower than the temperature required for the thermal annealing process. After confirming that the chamber is clean and free of process residue, the vacuum system can shut down the main pump group and maintain the vacuum level solely by relying on the chamber vacuum holding valve. The confirmation that the chamber is clean and free of process residue is automatic. The preferred judgment conditions include: the chamber pressure must be stable at 10. -6 The process gas concentration must be above Torr and last for more than 5 minutes; the concentration of process gas in the chamber must be below 0.01% and the oxygen concentration below 0.005%, as detected by the chamber's gas sensors; and the previous batch of process gas in the chamber must be a low-residue process (e.g., oxidation, annealing, etc., with a built-in process residue level list in the system), and a chamber cleaning procedure must have been performed after the previous batch was completed. If all the above conditions are met, the system automatically confirms that the chamber is clean and free of process residue; if any condition is not met, the system will automatically perform a chamber cleaning procedure (e.g., plasma cleaning) until the conditions are met before entering sleep mode. Other subsystems, such as the cooling water system, can switch to a low-power small-circulation mode or use a cold storage tank to maintain basic cooling; the process gas system can shut down the mass flow meter and valves to stop the gas supply.

[0069] In step S4, when the system reaches the safe wake-up time node at the current time node, it adjusts each system in the thermal annealing equipment from the dormant state to the process-ready state according to the process parameter information. Specifically, when the safe wake-up time node is reached at the current time node, the system will start the wake-up process of each subsystem according to the pre-acquired process parameter information. For example, the lamp heating system will adopt a multi-stage slope heating algorithm, initially applying higher power to rapidly raise the temperature. When approaching the target preheating temperature, it will switch to precise PID control to prevent overshoot. Through feedforward control and real-time monitoring of lamp resistance, it will ensure that the temperature rises stably from the storage temperature to the preheating temperature required by the process (e.g., 650°C) within 30 seconds. The vacuum system first starts the coarse pump to quickly evacuate the chamber to the medium vacuum range, and then starts the main pumps such as the molecular pump. Through the coordinated optimization of flow control and pressure PID, it restores the high vacuum or low vacuum environment required by the process (e.g., 10) within 30 seconds. -7During this process, each subsystem transitions from a low-power sleep state to a high-power process-ready state, and its operating parameters are adjusted to the target values ​​set by the process parameter information.

[0070] The following example illustrates the above technical solution in more detail: Suppose that in a chip manufacturing line, after a thermal annealing machine completes the processing of the current batch of wafers, its Manufacturing Execution System (MES) notifies the equipment control system that the estimated arrival time of the next batch of wafers is 3:00 PM, and the corresponding process recipe ID is "Annealing Process A". The equipment control system parses this information, obtains the estimated execution time node as 3:00 PM, and loads the process parameter information required for "Annealing Process A", such as a target temperature of 700°C and a vacuum degree of 10. -7 Meanwhile, the equipment control system queries the preset maximum wake-up time (e.g., 30 seconds). Based on the expected execution time (3:00 PM) and the maximum wake-up time (30 seconds), the system calculates the safe wake-up time as 2:59:30 PM. The current time is 1:00 PM. The system detects that the difference between the current time (1:00 PM) and the safe wake-up time (2:59:30 PM) (1 hour, 59 minutes, and 30 seconds) is greater than the preset threshold (e.g., 15 minutes). Therefore, the system determines that the equipment will have a relatively long idle time and triggers the thermal annealing equipment to enter a sleep state. Specifically, the lamp heating system lowers the temperature from the current operating temperature (e.g., 700°C) to the safe storage temperature (e.g., 80°C). After confirming that the chamber is clean and free of process residue, the vacuum system shuts down the main pump group and maintains the chamber vacuum level solely by relying on the chamber vacuum holding valve. The cooling water system switches to a low-power small circulation mode, and the process gas system shuts off the gas supply. In this sleep state, the overall operating power of the thermal annealing equipment is significantly reduced, thereby greatly reducing energy consumption. At 2:59:30 PM, the system detected that this time coincided with the safe wake-up time. At this point, the system initiated the wake-up process for each subsystem based on the pre-loaded process parameters of "Annealing Process A". The lamp heating system employs a multi-stage slope heating algorithm to stably raise the temperature from 80°C to 700°C within 30 seconds. The vacuum system first activates the roughing pump, then the molecular pump and other main pumps, restoring the chamber vacuum to 100°C within 25 seconds. -7 Torr, and other subsystems also synchronously returned to process-ready status. By 3:00 PM, all subsystems of the thermal annealing equipment had reached process-ready status, and all operating parameters met the requirements of "annealing process A," allowing for immediate processing of the next batch of wafers.

[0071] As can be seen from the above examples, the intelligent control method of this application enables the thermal annealing equipment to enter a low-power sleep state during non-production periods and to be precisely woken up before the start of the process task through accurate prediction and dynamic scheduling. Traditional thermal annealing equipment typically adopts a high-energy-consumption standby mode, meaning that regardless of whether there is a process task, the equipment's key subsystems (such as the lamp heating system and vacuum system) continue to operate or remain in a process-ready state, resulting in significant energy waste. For example, issues such as lamp preheating power consumption, continuous operation of the vacuum system, and subsystem idling cause the equipment to consume a large amount of electricity even during non-production periods. This application introduces the concepts of expected execution time node, maximum wake-up time, and safe wake-up time node, and combines them with a dynamic power consumption management strategy to achieve intelligent switching of equipment states. This method avoids unnecessary energy consumption when the equipment is idle for extended periods, while ensuring that the equipment can enter the process-ready state on time and accurately when needed, thereby significantly reducing the equipment's standby power consumption, improving energy utilization efficiency, and aligning with the trend of chip manufacturing transitioning towards more energy-efficient and sustainable green manufacturing.

[0072] In some preferred embodiments, step S1 includes:

[0073] S11. Obtain the estimated execution time node and process parameter information of the next process task to be executed in the current hot annealing equipment, and obtain the preset wake-up time corresponding to each system in the hot annealing equipment;

[0074] S12. Obtain environmental parameter information;

[0075] S13. For each system in the hot annealing equipment, obtain the cumulative runtime, historical operating parameters and historical maintenance information of that system;

[0076] S14. For each system in the hot annealing equipment, based on environmental parameter information and the system's corresponding cumulative runtime, historical operating parameters and historical maintenance information, the preset wake-up time of the system is corrected to obtain the corrected wake-up time of the system.

[0077] S15. Use the maximum value among all corrected wake-up times as the maximum wake-up time for the current thermal annealing device.

[0078] Obtaining environmental parameter information is to incorporate external environmental factors into the wake-up time consideration. Environmental parameter information may include, but is not limited to, ambient temperature, humidity, and atmospheric pressure. Specifically, significant changes in ambient temperature may affect the heating rate of the heating system or the cooling efficiency of the cooling system, thereby changing the actual wake-up time. In this embodiment, the environmental parameter information can be collected in real time by environmental sensors deployed around the equipment, or it can be obtained through a factory environmental monitoring system. Step S13 aims to collect key data reflecting the internal state and performance degradation of the equipment. Specifically, the cumulative runtime can be recorded by the equipment's internal timer or control system. This runtime reflects the equipment's usage intensity and aging degree. Historical operating parameters may include data such as temperature curves, pressure changes, and power consumption during past operation. These parameters can reveal the trend of equipment performance changes over time. Historical maintenance information may include equipment repair records, component replacement records, calibration records, etc. This information can reflect whether the equipment has undergone performance recovery or performance degradation due to component aging. This information can be obtained through the equipment's data acquisition system, historical database, or maintenance management system. For each system in the hot annealing equipment, the preset wake-up time for that system is corrected based on environmental parameters, cumulative runtime, historical operating parameters, and historical maintenance information. This correction process is the core of this solution, aiming to dynamically adjust the wake-up time to adapt to actual conditions. The correction can be calculated based on a preset mathematical model, such as establishing a relationship model between environmental parameters, cumulative runtime, historical operating parameters, and wake-up time through regression analysis; or it can be done by consulting a dynamically updated correction coefficient table to find the corresponding correction factor based on the current environment and equipment status. In this way, the preset wake-up time can be dynamically adjusted to better reflect the actual wake-up requirements of the equipment under the current environment and its own state. The maximum value among all corrected wake-up times is taken as the maximum wake-up time for the current hot annealing equipment to ensure that the entire hot annealing equipment can enter the process-ready state on time. Since hot annealing equipment typically contains multiple subsystems (such as heating systems, vacuum systems, gas supply systems, etc.), the time required for each system to recover from a dormant state to a process-ready state may differ. Choosing the maximum value among all corrected wake-up times ensures that even the slowest system can complete preparation before the expected execution time, thus avoiding delays in the entire process due to a subsystem failing to be ready in time.

[0079] This application's solution dynamically acquires and comprehensively analyzes environmental parameter information, cumulative equipment runtime, historical operating parameters, and historical maintenance information to correct the preset wake-up time corresponding to each system in the hot annealing equipment, thereby obtaining a more accurate corrected wake-up time. Based on this, the maximum value among all corrected wake-up times is taken as the maximum wake-up time for the current hot annealing equipment. This dynamic correction mechanism ensures that the maximum wake-up time reflects the actual wake-up needs of the equipment in the current environment and its own state, rather than relying on a fixed, potentially inaccurate, preset value. By incorporating this accurately corrected maximum wake-up time into the calculation of the safe wake-up time node, it ensures that the hot annealing equipment can reliably switch from sleep mode to process-ready mode on time when needed. This not only optimizes the equipment's sleep and wake-up strategy and reduces unnecessary standby power consumption, but also avoids process delays or product quality risks caused by inaccurate wake-up time estimation, thereby improving overall production efficiency and energy utilization.

[0080] The following is a concrete example to illustrate this. Suppose that the thermal annealing equipment needs to perform the annealing process for the next batch of wafers. First, the equipment control system obtains the estimated execution time node of the next process task, T_estimated, from the Manufacturing Execution System (MES), along with the corresponding process parameter information (such as target temperature 700°C, vacuum degree 10). -7(Torr). Simultaneously, the system obtains the initial preset wake-up time for each subsystem (such as the electric heating component and the vacuum pump assembly). For example, the preset wake-up time for the electric heating component is 25 seconds, and for the vacuum pump assembly it is 28 seconds. Next, the system uses environmental sensors to obtain the current ambient temperature of the workshop as 28°C and the ambient humidity as 60%. Simultaneously, the system queries the equipment's internal operating logs and maintenance records, obtaining that the electric heating component has accumulated 5000 hours of runtime, with a slight decreasing trend in its historical heating rate, and the most recent maintenance was three months ago; the vacuum pump assembly has accumulated 6000 hours of runtime, with a slightly longer time to reach the target vacuum level in its historical operation, and a recent pump oil change. Based on this information, the system uses a preset correction model (e.g., a machine learning model trained on historical data) to correct the preset wake-up time for each subsystem. For example, considering that the current high ambient temperature may slightly shorten the heating time, but the cumulative runtime and historical performance decline trend of the electric heating component may prolong its wake-up time, the correction model calculates a corrected wake-up time of 27 seconds for the electric heating component. For the vacuum pump unit, considering its cumulative runtime and historical performance degradation, but recent maintenance may have restored its performance, the modified model calculates a modified wake-up time of 29 seconds. Finally, the system compares all modified wake-up times (e.g., 27 seconds and 29 seconds) and takes the maximum value of 29 seconds as the maximum wake-up time for the current thermal annealing equipment. This maximum wake-up time of 29 seconds will be used to calculate subsequent safe wake-up time points to ensure that the equipment can reliably and timely enter the process-ready state.

[0081] In some preferred embodiments, step S2 includes:

[0082] S21. Obtain historical execution time fluctuation data of the current hot annealing equipment; the historical execution time fluctuation data includes the difference between at least one historical estimated execution time and the historical actual execution time.

[0083] S22. Determine the buffer time based on historical execution time fluctuation data;

[0084] S23. Calculate the safe wake-up time node based on the expected execution time node, buffer time, and maximum wake-up time.

[0085] Acquiring historical execution time fluctuation data for the current hot annealing equipment refers to the system collecting and storing information on the differences between the estimated and actual execution times of various process tasks performed by the hot annealing equipment over a past period. This difference data reflects the inherent uncertainties in production line operation. For example, in this embodiment, the estimated start time and actual start time of each process task can be recorded in real time by the equipment control system or manufacturing execution system (MES), and the difference can be calculated. These differences are then stored in the database as historical execution time fluctuation data. Determining the buffer time based on historical execution time fluctuation data refers to an additional amount of time reserved when calculating the safe wake-up time to cope with possible future execution time fluctuations. This buffer time aims to absorb uncertainties in the production process and ensure that the equipment has sufficient time to recover from the dormant state to the process-ready state. For example, statistical analysis can be performed on the collected historical execution time fluctuation data to calculate its standard deviation or variance, and then the statistic can be multiplied by a preset safety factor (e.g., 1.5) to obtain the buffer time. The safe wake-up time node is calculated based on the expected execution time node, buffer time, and maximum wake-up time. This refers to determining the latest point in time when the equipment must begin the wake-up process, taking into account the planned execution time of the process task, the safety margin reserved to cope with fluctuations, and the maximum time required for the equipment to wake up itself. Specifically, the safe wake-up time node can be calculated using the following formula: Safe wake-up time node = Expected execution time node - Buffer time - Maximum wake-up time. This ensures that the thermal annealing equipment can fully recover from its dormant state and reach a process-ready state before the expected execution time node of the process task arrives.

[0086] This application's solution incorporates historical execution time fluctuation data and buffer time to make the calculation of the safe wake-up time node more accurate and reliable. Specifically, the system first acquires historical execution time fluctuation data, which quantifies the time deviation in past process executions, providing an objective basis for subsequent buffer time calculations. Based on this, the system determines a buffer time according to this fluctuation data. This buffer time, as a safety margin, can effectively absorb uncertainties in production line operation and avoid wake-up decision errors caused by time fluctuations. Finally, this buffer time is combined with the expected execution time node and the maximum wake-up time to calculate a more accurate safe wake-up time node. This method not only optimizes the wake-up timing of the hot annealing equipment, enabling it to enter the process-ready state more precisely when needed, but also, combined with the method in the basic solution of acquiring the expected execution time node and the maximum wake-up time to calculate the safe wake-up time node, jointly constructs a more complete intelligent control strategy. Through this synergistic effect, the hot annealing equipment can avoid energy waste caused by premature wake-up and process delays caused by late wake-up, thereby achieving significant energy-saving effects while ensuring production efficiency and process quality.

[0087] In some preferred embodiments, step S23 includes:

[0088] S231. Obtain the operating status information of upstream equipment and the emergency order information of the production line where the current hot annealing equipment is located;

[0089] S232. Adjust the buffer time based on the operating status information and emergency order information;

[0090] S233. Analyze whether the adjusted buffer time is within the preset time range. If yes, then take the adjusted buffer time as the final buffer time. If no, then proceed to step S234.

[0091] S234. When the buffer time is greater than the upper limit of the preset time range, the upper limit of the preset time range shall be used as the final buffer time; when the buffer time is less than the lower limit of the preset time range, the lower limit of the preset time range shall be used as the final buffer time.

[0092] S235. Calculate the safe wake-up time node based on the expected execution time node, buffer time, and maximum wake-up time.

[0093] Obtaining the operational status information of upstream equipment refers to acquiring data on the working conditions of equipment that is related to the current hot annealing equipment in the production process. This information can reflect the production rhythm of upstream equipment and whether there are any abnormalities or potential delays. For example, in this embodiment, the real-time equipment load of upstream equipment can be obtained as its operational status through the Manufacturing Execution System (MES) or Supervisory Control and Data Acquisition (SCADA) interface. Obtaining emergency order insertion information for the production line where the current hot annealing equipment is located refers to obtaining high-priority production tasks temporarily inserted into the production plan. This information is usually issued by the MES system or production scheduling system. It can be obtained by querying production plan change notifications in real time through the system interface or by manually entering and confirming emergency order insertion commands. Buffer time is a time reserved to cope with uncertainties in the production process. Based on the real-time acquired operational status of upstream equipment and emergency order insertion information, this buffer time can be dynamically adjusted to better reflect the actual production situation. For example, when the upstream equipment is under high load or there is a fault warning, the buffer time can be appropriately increased to reserve more margin to deal with emergencies. Specifically, the adjustment method can be based on preset rules or logic. For example, if the upstream equipment load exceeds a certain threshold, the buffer time is increased by a fixed percentage; if an emergency order is detected, the buffer time is increased by another fixed percentage.

[0094] Step S233 analyzes whether the adjusted buffer time falls within the preset time range. The preset time range refers to a reasonable interval set for the buffer time, including an upper and lower limit. This range is designed to prevent the buffer time from becoming too long or too short due to over-adjustment. For example, based on historical production data, process requirements, and experience, the minimum buffer time can be set to 1 minute and the maximum to 5 minutes. This analysis is usually achieved through simple logical judgment, comparing the adjusted buffer time with the preset upper and lower limits.

[0095] When the buffer time exceeds the upper limit of the preset time range, the upper limit is used as the final buffer time; when the buffer time is less than the lower limit, the lower limit is used. If the adjusted buffer time exceeds the preset range, it needs to be forcibly corrected to ensure system stability and reliability. For example, if the calculated buffer time is too long, exceeding the upper limit, it is truncated to the upper limit to prevent premature device wake-up and reduced energy efficiency. Conversely, if the buffer time is too short, below the lower limit, it is increased to the lower limit to ensure sufficient margin for handling emergencies and prevent untimely device wake-up.

[0096] This application's solution effectively solves the problem of inaccurate buffer time determination in traditional solutions by incorporating upstream equipment operating status information and emergency order insertion information from the production line when calculating the safety wake-up time node, and dynamically adjusting the buffer time accordingly. Based on fundamental intelligent control methods, this solution acquires real-time operating status information from upstream equipment, such as equipment load and fault warnings, as well as emergency order insertion information from the production line, enabling timely responses to unexpected situations and dynamic changes on the production line, making the buffer time setting more timely and accurate. Furthermore, the adjusted buffer time is analyzed and limited within a preset range, preventing unreasonable excessive or insufficient buffer time due to over-adjustment, ensuring the stability and reliability of the buffer time. This dynamic adjustment and boundary constraint mechanism significantly improves the calculation accuracy of the safety wake-up time node, enabling more accurate prediction and response to uncertainties in the production process compared to methods relying solely on historical data.

[0097] As a specific implementation method, when calculating the safe wake-up time node, it is first necessary to obtain the operating status information of upstream equipment and the emergency order insertion information of the production line where the current hot annealing equipment is located. For example, the equipment control system can receive the utilization rate data of the upstream cleaning equipment in real time, and obtain information from the Manufacturing Execution System (MES) on whether there are emergency wafer batches with higher priority than the current task. Subsequently, the basic buffer time is dynamically adjusted based on this real-time information. For example, assuming that the basic buffer time obtained from historical data analysis is 120s, if the SCADA system shows that the real-time operating load of the upstream equipment has exceeded 80%, then according to the preset rules, the buffer time can be increased by 30%, that is, increased by 36s, making the buffer time 156s. If at the same time the MES system indicates that there is an emergency order insertion in the current production line, the buffer time can be further increased by 50%, that is, increased by another 78s on top of 156s, making the buffer time 234s. After the adjustment is completed, it is necessary to analyze whether the adjusted buffer time is within the preset time range. Assuming the preset buffer time range is 1 to 5 minutes, and the adjusted buffer time is 180 seconds, which falls within this preset range, 180 seconds will be directly adopted as the final buffer time. Finally, using this buffer time, which has been adjusted in real-time and constrained by boundaries, combined with the expected execution time and the maximum wake-up time, the safe wake-up time is precisely calculated. For example, if the expected execution time of the next process task is 10:00 AM, the maximum wake-up time is 30 seconds, and the final determined buffer time is 3 minutes, then the safe wake-up time will be calculated as 9:56:30 AM.

[0098] In some preferred embodiments, step S3 includes:

[0099] S31. When the difference between the current time node and the safe wake-up time node is greater than the preset threshold, record the state compensation parameters corresponding to each system in the current hot annealing equipment, and then adjust each system in the hot annealing equipment from the running state to the sleep state.

[0100] Step S4 includes:

[0101] S41. When the safe wake-up time node is reached at the current time node, adjust each system in the hot annealing equipment from the dormant state to the process ready state according to the process parameter information, and calibrate each system in the hot annealing equipment according to the state compensation parameters during the adjustment process.

[0102] To ensure the equipment can accurately return to a process-ready state after waking from hibernation, this application introduces the concept of state compensation parameters. These parameters are key data used to capture the operating characteristics or deviations of each system in the thermal annealing equipment before entering hibernation. For example, they may include baseline readings of various sensors under specific conditions, calibration coefficients, or characteristic curves or models describing the performance of key components. By recording these parameters, the system can provide a reliable reference benchmark for subsequent accurate recovery. When the system needs to enter hibernation, each system in the thermal annealing equipment adjusts from a high-energy-consumption operating state to a low-energy-consumption hibernation state. This adjustment process can be achieved by gradually reducing the power of each system, shutting down unnecessary components, or switching some components to a low-power standby mode to maximize energy savings. When the equipment needs to wake from hibernation and prepare to execute the next process task, the system adjusts each system in the thermal annealing equipment from hibernation to a process-ready state according to preset process parameter information. This process typically involves gradually starting each system in a predetermined sequence and bringing it to the target values ​​such as temperature, vacuum, and gas flow rate required by the process. During this adjustment process, the system will use the previously recorded state compensation parameters to calibrate each system in the thermal annealing equipment. The calibration mechanism can be to correct the offset of sensor readings in real time to compensate for parameter drift or component aging effects that may occur during the dormant period, so as to ensure that each system can accurately and stably reach the process-ready state.

[0103] This application's solution proactively records the state compensation parameters of each system before the hot annealing equipment enters a dormant state, and uses these parameters to calibrate each system during the process of the equipment waking up from dormant to process-ready state, thereby solving the problem of decreased process accuracy and increased energy consumption caused by equipment parameter drift. Specifically, the intelligent control method calculates a safe wake-up time node based on the expected execution time node and the maximum wake-up time. When the difference between the current time node and the safe wake-up time node exceeds a preset threshold, the system adjusts each system in the hot annealing equipment from the operating state to a dormant state to save energy. Before this, the system captures and records the key state compensation parameters of each system, which reflect the precise characteristics of the equipment under normal operating conditions. When the current time node reaches the safe wake-up time node, the system begins the wake-up process, adjusting each system from a dormant state to a process-ready state based on process parameter information. During this crucial adjustment phase, the system does not simply restore to the preset value, but uses the previously recorded state compensation parameters to perform fine-tuning calibration on each system. For example, for sensors or actuators that may drift due to temperature changes or prolonged downtime, the system corrects their output or control logic in real time based on recorded compensation parameters, ensuring that all performance indicators accurately match process requirements when reaching the process-ready state. This pre-recording and dynamic calibration mechanism enables the thermal annealing equipment to quickly and accurately reach the stable state required by the process when recovering from energy-saving sleep mode, avoiding additional debugging time or process defects caused by parameter drift. Thus, it achieves energy saving while ensuring the accuracy and stability of the process.

[0104] In some preferred embodiments, the thermal annealing apparatus includes an electric heating component and a vacuum gauge. The state compensation parameters include the resistance and temperature variation curves corresponding to the electric heating component and the zero-point offset background value corresponding to the vacuum gauge. The process of calibrating each system in the thermal annealing apparatus according to the state compensation parameters includes:

[0105] A1. Obtain the real-time temperature and resistance value of the electric heating component;

[0106] A2. Extract the corresponding temperature from the curve of resistance and temperature change based on the real-time resistance value as the reference temperature;

[0107] A3. Based on the deviation between the reference temperature and the real-time temperature, obtain the resistance and temperature change curves to obtain the resistance and temperature correction curves, and then control the temperature of the electric heating component based on the resistance and temperature correction curves.

[0108] A4. Obtain the real-time zero point value of the vacuum gauge;

[0109] A5. The vacuum level measured by the vacuum gauge is calibrated based on the deviation between the real-time zero point value and the zero point offset background value.

[0110] The electric heating element can be a heating unit used to provide thermal energy. For example, it can be a lamp heating system that radiates heat to the wafer using a high-power lamp, or a resistance wire heater that generates Joule heat by current flowing through a resistance wire. The vacuum gauge can be a sensor used to measure the pressure inside the chamber. For example, it can be an ionization vacuum gauge that determines pressure by measuring the ionization current of a gas, or a Pirani vacuum gauge that determines pressure by measuring changes in the resistance of a hot wire. The state compensation parameters can include the resistance-temperature variation curves corresponding to the electric heating element and the zero-point offset background value corresponding to the vacuum gauge. The resistance-temperature variation curves are curves used to describe the nonlinear relationship between the resistance and temperature of the electric heating element, and the zero-point offset background value can be the vacuum gauge reading recorded before the device goes into sleep mode under a preset ultra-high vacuum environment.

[0111] In calibrating each system in the thermal annealing equipment according to the condition compensation parameters, the real-time temperature and resistance values ​​of the electric heating components need to be obtained first. The real-time temperature can be monitored and acquired in real time using devices such as thermocouple sensors, infrared thermometers, or resistance thermometers. The real-time resistance value can be accurately measured using a Wheatstone bridge circuit, a digital multimeter, or a dedicated resistance measurement module. Next, the corresponding temperature is extracted from the resistance-temperature curve based on the real-time resistance value as a reference temperature. This extraction process involves substituting the real-time resistance value into the resistance-temperature curve. Then, the resistance-temperature curve is corrected based on the deviation between the reference temperature and the real-time temperature to obtain a correction curve for resistance and temperature. The temperature of the electric heating components is then controlled based on this correction curve. The deviation correction can employ a linear correction algorithm, adjusting the curve proportionally according to the magnitude of the deviation. Specifically, the correction formula is: Correction curve for resistance and temperature = Resistance-temperature curve + Temperature difference × Correction coefficient (preset value or dynamically confirmed based on the aging degree of the electric heating components). At the same time, it is also necessary to obtain the real-time zero point value of the vacuum gauge. The real-time zero point value can be obtained by making the vacuum gauge perform self-calibration measurement in a specific known low pressure or ultra-high vacuum environment after the device is woken up. Then, the vacuum degree measured by the vacuum gauge is calibrated according to the deviation between the real-time zero point value and the zero point offset background value. The deviation calibration can be that the difference between the real-time zero point value and the background value is directly used as the offset and added or subtracted to the real-time measurement value of the vacuum gauge.

[0112] This application's solution addresses parameter drift issues caused by equipment aging or environmental changes by dynamically and precisely calibrating key electric heating components and vacuum gauges when the thermal annealing equipment transitions from a dormant to a process-ready state. Before the equipment enters the process-ready state, the system actively acquires the real-time temperature and resistance values ​​of the electric heating components. By mapping the real-time resistance values ​​to a preset resistance-temperature curve, a reference temperature is obtained and compared with the actual measured real-time temperature. If a deviation exists, it indicates that the resistance-temperature characteristic curve may have drifted. The system dynamically corrects the curve based on this deviation, generating a calibration curve. This calibration curve is then used to precisely control the temperature of the electric heating components, ensuring accurate and stable heat delivery in the process-ready state. Simultaneously, for the vacuum gauge, the system acquires its current real-time zero-point value and compares it with the zero-point offset background value recorded before dormancy. Any difference is identified as zero-point drift, and the system uses this deviation to compensate and calibrate the vacuum gauge's measurement results, thereby ensuring the accuracy of vacuum measurement. This dual calibration mechanism, combined with the aforementioned scheme of adjusting each system in the hot annealing equipment from a dormant state to a process-ready state and calibrating each system according to state compensation parameters during the adjustment process, effectively overcomes the uncertainty caused by component parameter drift when the equipment quickly recovers from an energy-saving dormant mode to a high-precision operating state. This approach not only avoids process failures or product quality degradation due to inaccurate parameters but also reduces additional energy consumption caused by repeated debugging or excessive preheating time, ensuring the high efficiency and reliability of the equipment in intelligent standby-wake-up mode.

[0113] In some preferred embodiments, the intelligent sleep / wake-up method based on active prediction further includes the step of:

[0114] B1. When adjusting each system in the hot annealing equipment from a dormant state to a process-ready state and an upstream equipment failure occurs, acquire upstream equipment failure parameter information and upstream equipment process progress information; the failure parameter information includes the failure type and failure severity.

[0115] B2. Based on the fault parameter information and the upstream equipment process progress information, generate the predicted execution time node for the next process task to be executed by the current hot annealing equipment;

[0116] B3. Analyze whether the deviation between the predicted execution time node and the expected execution time node is greater than the preset time threshold. If yes, proceed to step B4. If no, continue to adjust each system in the hot annealing equipment from the dormant state to the process ready state according to the process parameter information, and return to step B1.

[0117] B4. Recalculate the safe wake-up time node based on the predicted execution time node and the maximum wake-up time, and adjust each system in the hot annealing equipment to the intermediate maintenance state; for each system in the hot annealing equipment, the operating power of the system in the intermediate maintenance state is less than its operating power in the process ready state and greater than its operating power in the dormant state.

[0118] B5. When the recalculated safe wake-up time point is reached at the current time point, adjust each system in the hot annealing equipment from the intermediate maintenance state to the process ready state according to the process parameter information.

[0119] When adjusting each system in the hot annealing equipment from a dormant state to a process-ready state and an upstream equipment failure occurs, the system first acquires upstream equipment fault parameter information and upstream equipment process progress information. The fault parameter information can include the fault type (e.g., mechanical fault, electrical fault, software fault, process abnormality, etc.) and the fault severity (e.g., minor warning, moderate downtime, severe production stoppage, etc.). This embodiment obtains the fault parameter information by communicating with the Manufacturing Execution System (MES) or Equipment Automation System (EAP) via a data interface, receiving real-time data such as the operating status of upstream equipment, alarm information, and production plan adjustments.

[0120] Subsequently, based on fault parameter information and upstream equipment process progress information, the predicted execution time node for the next process task to be executed by the current hot annealing equipment is generated. This step aims to dynamically calculate the actual start time of the next process task of the current hot annealing equipment based on the actual fault situation and production progress of the upstream equipment. The generation method can be either through a built-in scheduling optimization algorithm, combined with information such as fault type, severity, estimated repair time, currently completed process steps of the upstream equipment, and remaining process steps to be completed, to recalculate a new estimated execution time; or through a machine learning model, based on historical fault data and production scheduling adjustment records, to predict the execution time node.

[0121] Next, the deviation between the predicted execution time and the expected execution time is analyzed to determine if it exceeds a preset time threshold. This step assesses the impact of upstream failures on the original plan of the thermal annealing equipment. This impact can be quantified by comparing the newly generated predicted execution time with the initial expected execution time. The preset time threshold is a configurable parameter that defines the level of deviation required to trigger further adjustments. For example, this threshold can be set to 5 minutes, 10 minutes, or longer. If the deviation between the predicted and expected execution time is greater than the preset time threshold, subsequent adjustment steps are executed. If the deviation is less than or equal to the preset time threshold, the upstream failure is considered to have little impact on the current task, and the thermal annealing equipment can continue to wake up according to the original plan, returning to step B1 to continuously monitor the status of upstream equipment and respond to any further changes that may occur.

[0122] When the deviation exceeds a preset time threshold, the safe wake-up time is recalculated based on the predicted execution time and maximum wake-up time, and each system in the thermal annealing equipment is adjusted to an intermediate maintenance state. This step ensures that the equipment does not enter the fully ready state too early or too late. The intermediate maintenance state is a transitional operating mode between full hibernation and full process readiness. In this state, each system in the thermal annealing equipment operates at a power level higher than in the hibernation state but lower than in the process readiness state to maintain a certain preheating, pre-vacuum, or preparatory state, thereby enabling it to reach the process readiness state more quickly when needed, while avoiding the high energy consumption associated with full wake-up. For example, the heating system can be maintained at a lower but higher temperature than the hibernation temperature, the vacuum system can be maintained at a medium vacuum level, and the cooling system can maintain a low-speed circulation. For each system in the thermal annealing equipment, the operating power of the system in the intermediate maintenance state is less than its operating power in the process readiness state but greater than its operating power in the hibernation state.

[0123] Finally, when the recalculated safe wake-up time is reached at the current time point, each system in the hot annealing equipment is adjusted from the intermediate maintenance state to the process-ready state based on the process parameter information. This process utilizes the preparatory advantage of the intermediate maintenance state to ensure that the equipment can be put into production in a timely and efficient manner.

[0124] Through the above technical solution, this application effectively solves the problem of energy waste and equipment damage caused by task delays due to upstream equipment failures during the adjustment process of hot annealing equipment from a dormant state to a process-ready state. Based on the intelligent control method for hot annealing equipment described above, this solution introduces a dynamic response mechanism for upstream equipment failures. When an upstream equipment failure occurs, the system can promptly acquire fault parameter information and process progress information, and generate a more accurate predicted execution time node accordingly. By analyzing the deviation between the predicted execution time node and the expected execution time node, the system can intelligently determine whether to adjust the equipment state. When the deviation is large, the equipment will not blindly enter a high-energy-consuming process-ready state, but will be adjusted to an intermediate maintenance state with operating power between the dormant state and the process-ready state. This intermediate maintenance state can significantly reduce the energy consumption of the equipment during the waiting period, and maintain certain preparatory conditions to ensure that the equipment can quickly and efficiently enter the process-ready state when the new safe wake-up time node arrives. Therefore, this solution minimizes unnecessary energy consumption and improves the overall operating economy of the hot annealing equipment while ensuring production continuity and efficiency.

[0125] As can be seen from the above, the intelligent sleep-wake method based on active prediction provided in this application introduces the concepts of expected execution time node, maximum wake-up time and safe wake-up time node, and combines them with dynamic power consumption management strategy to realize intelligent switching of device state. This method avoids unnecessary energy consumption when the device is idle for a long time, and at the same time ensures that the device can enter the process-ready state on time and accurately when needed, thereby significantly reducing the standby power consumption of the device and improving energy utilization efficiency.

[0126] Secondly, such as Figure 2 As shown, this application also provides an intelligent sleep / wake-up device based on active prediction, which includes:

[0127] The parameter acquisition module 1 is used to acquire the estimated execution time node and process parameter information of the next process task to be executed by the current hot annealing equipment, and to acquire the maximum wake-up time of the current hot annealing equipment; the maximum wake-up time is the maximum value of the preset wake-up time corresponding to each system in the hot annealing equipment.

[0128] Node calculation module 2 is used to calculate the safe wake-up time node based on the expected execution time node and the maximum wake-up time.

[0129] The hibernation switching module 3 is used to switch each system in the thermal annealing equipment from the running state to the hibernation state when the difference between the current time node and the safe wake-up time node is greater than a preset threshold.

[0130] The wake-up switching module 4 is used to adjust each system in the hot annealing equipment from the dormant state to the process-ready state according to the process parameter information when the safe wake-up time node is reached at the current time node. For each system in the hot annealing equipment, the operating power of the system in the dormant state is less than its operating power in the process-ready state, and the operating parameters of the system in the process-ready state are the process parameter information.

[0131] The present application provides an intelligent sleep / wake-up device based on active prediction, comprising a parameter acquisition module 1, a node calculation module 2, a sleep switching module 3, and a wake-up switching module 4. The intelligent sleep / wake-up device based on active prediction provided in this embodiment is preferably used to execute the steps in the intelligent sleep / wake-up method based on active prediction provided in the first aspect above. The principle of the intelligent sleep / wake-up device based on active prediction provided in this embodiment is the same as the principle of the intelligent sleep / wake-up method based on active prediction provided in the first aspect above, and will not be repeated here.

[0132] Please refer to Figure 3 , Figure 3 This application provides a schematic diagram of the structure of an electronic device according to an embodiment of the present application. The electronic device includes a processor 101 and a memory 102. The processor 101 and the memory 102 are interconnected and communicate with each other via a communication bus 103 and / or other forms of connection mechanisms (not shown). The memory 102 stores computer-readable instructions executable by the processor 101. When the electronic device is running, the processor 101 executes these computer-readable instructions to perform the method in any optional implementation of the above embodiments, thereby achieving the following function: Step S1: Obtain the estimated execution time node and process parameter information of the next process task to be executed by the current thermal annealing equipment, and obtain the maximum wake-up time of the current thermal annealing equipment. The maximum wake-up time is the maximum value of the preset wake-up time for each system in the thermal annealing equipment; Step S2: Calculate the safe wake-up time node based on the expected execution time node and the maximum wake-up time; Step S3: When the difference between the current time node and the safe wake-up time node is greater than the preset threshold, adjust each system in the thermal annealing equipment from the running state to the sleep state; Step S4: When the safe wake-up time node is reached at the current time node, adjust each system in the thermal annealing equipment from the sleep state to the process ready state according to the process parameter information; For each system in the thermal annealing equipment, the operating power of the system in the sleep state is less than its operating power in the process ready state, and the operating parameters of the system in the process ready state are the process parameter information.

[0133] This application embodiment also provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it executes the method in any optional implementation of the above embodiments to achieve the following functions: Step S1: Obtain the estimated execution time node and process parameter information of the next process task to be executed by the current hot annealing equipment, and obtain the maximum wake-up time of the current hot annealing equipment; the maximum wake-up time is the maximum value of the preset wake-up time corresponding to each system in the hot annealing equipment; Step S2: Calculate the safe wake-up time node according to the estimated execution time node and the maximum wake-up time; Step S3: When the difference between the current time node and the safe wake-up time node is greater than a preset threshold, adjust each system in the hot annealing equipment from the running state to the dormant state; Step S4: When the current time node reaches the safe wake-up time node, adjust each system in the hot annealing equipment from the dormant state to the process-ready state according to the process parameter information; For each system in the hot annealing equipment, the operating power of the system in the dormant state is less than its operating power in the process-ready state, and the operating parameters of the system in the process-ready state are the process parameter information. The computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0134] As can be seen from the above, the intelligent sleep-wake method, device, equipment and medium based on active prediction provided in this application, by introducing the concepts of expected execution time node, maximum wake-up time and safe wake-up time node, and combining them with dynamic power consumption management strategy, realizes intelligent switching of device state. This method avoids unnecessary energy consumption when the device is idle for a long time, while ensuring that the device can enter the process-ready state on time and accurately when needed, thereby significantly reducing the standby power consumption of the device and improving energy utilization efficiency.

[0135] In the embodiments provided in this application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of the above units is only a logical functional division, and there may be other division methods in actual implementation. Furthermore, multiple units or components may be combined or integrated into another robot, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interface; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0136] Furthermore, the units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0137] Furthermore, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0138] In this document, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, without necessarily requiring or implying any such actual relationship or order between these entities or operations.

[0139] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A smart sleep / wake-up method based on active prediction, applied in a thermal annealing equipment, characterized in that, The intelligent sleep / wake method based on active prediction includes the following steps: S1. Obtain the estimated execution time node and process parameter information of the next process task to be executed by the current hot annealing equipment, and obtain the maximum wake-up time of the current hot annealing equipment; the maximum wake-up time is the maximum value of the preset wake-up time corresponding to each system in the hot annealing equipment; S2. Calculate the safe wake-up time node based on the expected execution time node and the maximum wake-up time; S3. When the difference between the current time node and the safe wake-up time node is greater than a preset threshold, adjust each system in the thermal annealing equipment from the running state to the sleep state. S4. When the safe wake-up time node is reached at the current time node, each system in the hot annealing equipment is adjusted from the dormant state to the process ready state according to the process parameter information; for each system in the hot annealing equipment, the operating power of the system in the dormant state is less than its operating power in the process ready state, and the operating parameters of the system in the process ready state are the process parameter information.

2. The intelligent sleep / wake-up method based on active prediction according to claim 1, characterized in that, Step S1 includes: S11. Obtain the estimated execution time node and process parameter information of the next process task to be executed by the current hot annealing equipment, and obtain the preset wake-up time corresponding to each system in the hot annealing equipment; S12. Obtain environmental parameter information; S13. For each system in the hot annealing equipment, obtain the cumulative runtime, historical operating parameters and historical maintenance information of that system; S14. For each system in the hot annealing equipment, based on the environmental parameter information and the system's corresponding cumulative runtime, historical operating parameters and historical maintenance information, the preset wake-up time of the system is corrected to obtain the corrected wake-up time of the system. S15. Take the maximum value among all the corrected wake-up times as the current maximum wake-up time of the thermal annealing device.

3. The intelligent sleep / wake-up method based on active prediction according to claim 1, characterized in that, Step S2 includes: S21. Obtain historical execution time node fluctuation data of the current hot annealing equipment; the historical execution time node fluctuation data includes at least one historical estimated execution time node and historical actual execution time node difference; S22. Determine the buffer time based on the historical execution time fluctuation data; S23. Calculate the safe wake-up time node based on the expected execution time node, the buffer time, and the maximum wake-up time.

4. The intelligent sleep / wake-up method based on active prediction according to claim 3, characterized in that, Step S23 includes: S231. Obtain the operating status information of the upstream equipment and the emergency order information of the production line where the current hot annealing equipment is located; S232. Adjust the buffer time according to the operating status information and the emergency order information; S233. Analyze whether the adjusted buffer time is within the preset time range. If yes, then take the adjusted buffer time as the final buffer time. If no, then proceed to step S234. S234. When the buffer time is greater than the upper limit of the preset time range, the upper limit of the preset time range shall be used as the final buffer time; when the buffer time is less than the lower limit of the preset time range, the lower limit of the preset time range shall be used as the final buffer time. S235. Calculate the safe wake-up time node based on the expected execution time node, the buffer time, and the maximum wake-up time.

5. The intelligent sleep / wake-up method based on active prediction according to claim 1, characterized in that, Step S3 includes: S31. When the difference between the current time node and the security wake-up time node is greater than a preset threshold, record the state compensation parameters corresponding to each system in the current thermal annealing equipment, and then adjust each system in the thermal annealing equipment from the running state to the sleep state. Step S4 includes: S41. When the safe wake-up time node is reached at the current time node, each system in the hot annealing equipment is adjusted from the dormant state to the process ready state according to the process parameter information, and during the adjustment process, each system in the hot annealing equipment is calibrated according to the state compensation parameters.

6. The intelligent sleep / wake-up method based on active prediction according to claim 5, characterized in that, The thermal annealing equipment includes an electric heating component and a vacuum gauge. The state compensation parameters include the resistance and temperature variation curves of the electric heating component and the zero-point offset background value of the vacuum gauge. The process of calibrating each system in the thermal annealing equipment according to the state compensation parameters includes: A1. Obtain the real-time temperature and real-time resistance value of the electric heating component; A2. Extract the corresponding temperature from the resistance and temperature change curve based on the real-time resistance value as a reference temperature; A3. Correct the resistance and temperature variation curves based on the deviation between the reference temperature and the real-time temperature to obtain a correction curve for resistance and temperature, and then control the temperature of the electric heating component based on the correction curve for resistance and temperature. A4. Obtain the real-time zero point value of the vacuum gauge; A5. The vacuum level measured by the vacuum gauge is calibrated based on the deviation between the real-time zero point value and the zero point offset background value.

7. The intelligent sleep / wake-up method based on active prediction according to claim 1, characterized in that, The intelligent sleep-wake method based on active prediction further includes the following steps: B1. When each system in the hot annealing equipment is adjusted from the dormant state to the process-ready state and an upstream equipment fails, obtain the upstream equipment fault parameter information and the upstream equipment process progress information. The fault parameter information includes the fault type and fault severity; B2. Based on the fault parameter information and the upstream equipment process progress information, generate the predicted execution time node for the next process task to be executed by the current hot annealing equipment; B3. Analyze whether the deviation between the predicted execution time node and the expected execution time node is greater than a preset time threshold. If yes, proceed to step B4. If no, continue to adjust each system in the hot annealing equipment from the dormant state to the process ready state according to the process parameter information, and return to step B1. B4. Recalculate the safe wake-up time node based on the predicted execution time node and the maximum wake-up time, and adjust each system in the thermal annealing equipment to the intermediate maintenance state. For each system in the hot annealing equipment, the operating power of the system in the intermediate maintenance state is less than its operating power in the process-ready state but greater than its operating power in the dormant state. B5. When the recalculated safe wake-up time node is reached at the current time node, each system in the thermal annealing equipment is adjusted from the intermediate maintenance state to the process ready state according to the process parameter information.

8. A smart sleep / wake-up device based on active prediction, applied in a thermal annealing equipment, characterized in that, The intelligent sleep / wake-up device based on active prediction includes: The parameter acquisition module is used to acquire the estimated execution time node and process parameter information of the next process task to be executed by the current hot annealing equipment, and to acquire the maximum wake-up time of the current hot annealing equipment; the maximum wake-up time is the maximum value of the preset wake-up time corresponding to each system in the hot annealing equipment; The node calculation module is used to calculate the safe wake-up time node based on the expected execution time node and the maximum wake-up time. The hibernation switching module is used to switch each system in the thermal annealing equipment from the running state to the hibernation state when the difference between the current time node and the safe wake-up time node is greater than a preset threshold. The wake-up switching module is used to adjust each system in the hot annealing equipment from a dormant state to a process-ready state according to the process parameter information when the safe wake-up time node is reached at the current time node; for each system in the hot annealing equipment, the operating power of the system in the dormant state is less than its operating power in the process-ready state, and the operating parameters of the system in the process-ready state are the process parameter information.

9. An electronic device, characterized in that, It includes a processor and a memory, the memory storing computer-readable instructions that, when executed by the processor, perform the steps of the method as described in any one of claims 1-7.

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 performs the steps of the method as described in any one of claims 1-7.

Images