Clean room temperature and humidity intelligent control method and system based on digital twinning

Abstract

This application provides a method and system for intelligent control of cleanroom temperature and humidity based on digital twins, relating to the field of intelligent control technology, and solving the technical problems of real-time performance and dynamic response lag in cleanroom temperature and humidity control in existing technologies. The method includes: constructing a digital twin model simulating the temperature and humidity distribution and airflow state within a cleanroom; acquiring real-time data from the cleanroom at a first moment using multi-source sensors; the multi-source sensors include at least multiple high-precision temperature and humidity sensors; calibrating the parameters of the digital twin model by comparing the actual data with the first simulated value of the digital twin model for the first moment; inputting the actual data into the digital twin model to obtain a second simulated value of the digital twin model for a second moment; and outputting control commands based on the deviation between the second simulated value and a set standard value to drive the physical equipment to execute.

Description

Technical Field

[0001] This application relates to the field of intelligent control technology, and in particular to a method and system for intelligent control of cleanroom temperature and humidity based on digital twins. Background Technology

[0002] In recent years, optical components (such as optical splitters, fiber optic connectors, and pre-terminated drop cables) have played an increasingly important role in communication networks. The performance and stability of these products directly affect the operational efficiency and quality of the entire communication system. Therefore, rigorous testing and quality control of these products are essential during the production process. Constant temperature and humidity cleanroom testing systems are designed to meet this need, providing a stable and controllable testing environment for optical components and ensuring the accuracy and reliability of test results.

[0003] Cleanroom environments are susceptible to various unexpected disturbances, such as equipment start-up and shutdown, and frequent personnel entry and exit. Traditional temperature and humidity control systems often rely on fixed threshold controls, which cannot respond quickly and adjust in time to these disturbances, causing environmental parameters to deviate from the set values ​​for extended periods. Summary of the Invention

[0004] This application provides a method and system for intelligent control of cleanroom temperature and humidity based on digital twins, which solves the technical problems of real-time control and dynamic response lag in cleanroom temperature and humidity control in the prior art.

[0005] To achieve the above objectives, this application adopts the following technical solution: Firstly, a method for intelligent control of cleanroom temperature and humidity based on digital twins is provided, comprising: constructing a digital twin model simulating the temperature and humidity distribution and airflow state in a cleanroom; acquiring real-time data of the cleanroom at a first moment using multi-source sensors; the multi-source sensors including at least multiple high-precision temperature and humidity sensors; calibrating the parameters of the digital twin model by comparing the actual data with the first simulated value of the digital twin model for the first moment; inputting the actual data into the digital twin model to obtain the second simulated value of the digital twin model for the second moment; and outputting control commands based on the deviation between the second simulated value and a set standard value to drive the physical equipment to execute.

[0006] Based on the above technical solution, the intelligent control method for cleanroom temperature and humidity based on digital twins provided in this application achieves millimeter-level precision simulation of the cleanroom environment by constructing a digital twin model that simulates the temperature and humidity distribution and airflow state within the cleanroom. By combining real-time data collected from multi-source sensors and continuously calibrating the model parameters, the accuracy of temperature and humidity control is significantly improved. Furthermore, by collecting actual data in real time and combining it with the rapid simulation capabilities of the digital twin model, environmental change trends can be predicted in a short time, allowing for proactive control decisions and effectively enhancing the system's real-time performance and dynamic response capabilities.

[0007] In conjunction with the first aspect mentioned above, in one possible implementation, the method for constructing a digital twin model simulating the temperature and humidity distribution and airflow state in a cleanroom specifically includes: constructing a geometric model based on the physical layout of the cleanroom; and incorporating physical characteristic equations to establish the correlation between equipment operating parameters and the temperature, humidity, and airflow fields.

[0008] In conjunction with the first aspect mentioned above, in one possible implementation, the method further includes: integrating a dual-objective reward function of temperature and humidity compliance rate and energy consumption into the digital twin model; performing offline pre-training in the digital twin model using a reinforcement learning algorithm, and then fine-tuning it online in the cleanroom to ensure that the control commands meet the preset temperature and humidity compliance rate threshold and energy consumption reduction threshold.

[0009] In conjunction with the first aspect mentioned above, in one possible implementation, the formula for calculating the bi-objective reward function is as follows: ; It is a bi-objective reward function; Rewards will be given for meeting temperature and humidity standards; As an energy consumption reward; , The target weight coefficient is α+β=1; When the temperature and humidity deviation is within the preset range, the formula for calculating the temperature and humidity compliance bonus is as follows: ; Basic reward value; This is the deviation penalty coefficient; Temperature deviation; Humidity deviation; When the temperature and humidity deviation exceeds the preset range, the formula for calculating the temperature and humidity compliance bonus is as follows: ; This refers to the penalty coefficient for exceeding the limit; The formula for calculating energy consumption bonus is: ; Basic energy consumption bonus value; This is the energy consumption penalty coefficient. If the current total energy consumption exceeds the preset percentage of the rated maximum total energy consumption, the energy consumption reward will be negative.

[0010] In conjunction with the first aspect above, in one possible implementation, the method further includes: adjusting the target weight coefficient according to the cleanroom's operating scenario; when the cleanroom's operating scenario is a testing operation, increasing the target weight coefficient for temperature and humidity compliance rewards and decreasing the target weight coefficient for energy consumption rewards; when the cleanroom's operating scenario is a non-testing operation, decreasing the target weight coefficient for temperature and humidity compliance rewards and increasing the target weight coefficient for energy consumption rewards.

[0011] In conjunction with the first aspect mentioned above, in one possible implementation, the method further includes: collecting the equipment operating parameters of the physical equipment in the cleanroom at a first moment; correcting the equipment performance degradation factor by comparing the equipment operating parameters with the first predicted operating parameters of the digital twin model for the physical equipment at the first moment, so that the degradation state of the digital twin model is consistent with that of the physical equipment; inputting the equipment operating parameters into the digital twin model to obtain the second predicted operating parameters of the digital twin model for the physical equipment at a second moment; and predicting the performance degradation trend and remaining lifespan of the physical equipment based on the second predicted operating parameters, generating early warning information and maintenance suggestions.

[0012] In conjunction with the first aspect above, in one possible implementation, the method for predicting the performance degradation trend and remaining lifespan of a physical device based on the second predicted operating parameters specifically includes: constructing a performance degradation curve of the physical device; or, training the predicted operating parameters output by the digital twin model through a deep learning network, so that the trained deep learning network outputs the performance degradation trend and remaining lifespan.

[0013] In conjunction with the first aspect mentioned above, in one possible implementation, the deployment density of the aforementioned multiple high-precision temperature and humidity sensors is greater than a preset density; the multi-source sensors also include: a laser particle counter and an infrared thermal imager.

[0014] In conjunction with the first aspect mentioned above, in one possible implementation, the method further includes: setting temperature and humidity requirements for multiple application scenarios in the digital twin model; if the application scenario of the cleanroom changes, adjusting the digital twin model according to the temperature and humidity requirements of the corresponding scenario.

[0015] Secondly, a cleanroom temperature and humidity intelligent control system based on digital twins is provided, comprising: a model building module, a multi-source data acquisition module, and an intelligent control module; the model building module is used to construct a digital twin model simulating the temperature and humidity distribution and airflow state in the cleanroom; the multi-source data acquisition module is used to collect the actual data of the cleanroom in real time at a first moment through multi-source sensors; the multi-source sensors include at least multiple high-precision temperature and humidity sensors; the model building module is also used to calibrate the parameters of the digital twin model by comparing the actual data with the first simulation value of the digital twin model for the first moment; the intelligent control module is used to input the actual data into the digital twin model to obtain the second simulation value of the digital twin model for a second moment; the intelligent control module is also used to output control commands based on the deviation between the second simulation value and the set standard value to drive the physical equipment to execute.

[0016] Thirdly, this application provides a cleanroom temperature and humidity intelligent control device based on digital twins, comprising: a processor and a storage medium; the storage medium includes instructions, and the processor is used to execute the instructions to implement the methods described in the first aspect and any possible implementation thereof. This cleanroom temperature and humidity intelligent control device based on digital twins can be an electronic device or a chip within an electronic device.

[0017] Fourthly, this application provides a cleanroom temperature and humidity intelligent control device based on digital twins, comprising: a communication unit and a processing unit; the processing unit is used to construct a digital twin model simulating the temperature and humidity distribution and airflow state in a cleanroom; the processing unit is also used to collect actual data of the cleanroom in real time at a first moment through multi-source sensors; the multi-source sensors include at least multiple high-precision temperature and humidity sensors; the processing unit is also used to calibrate the parameters of the digital twin model by comparing the actual data with the first simulated value of the digital twin model for the first moment; the processing unit is also used to input the actual data into the digital twin model to obtain the second simulated value of the digital twin model for a second moment; the communication unit is used to output control commands based on the deviation between the second simulated value and a set standard value to drive the physical device to execute.

[0018] Fifthly, this application provides a computer-readable storage medium storing instructions that, when executed on a digital twin-based cleanroom temperature and humidity intelligent control device, cause the digital twin-based cleanroom temperature and humidity intelligent control device to perform the methods described in the first aspect and any possible implementation thereof.

[0019] In a sixth aspect, this application provides a computer program product containing instructions that, when the computer program product is run on a digital twin-based cleanroom temperature and humidity intelligent control device, causes the digital twin-based cleanroom temperature and humidity intelligent control device to perform the methods described in the first aspect and any possible implementation thereof.

[0020] This application provides a method and system for intelligent control of cleanroom temperature and humidity based on digital twins. By constructing a digital twin model simulating the temperature, humidity distribution, and airflow conditions within a cleanroom, millimeter-level precision simulation of the cleanroom environment is achieved. Combined with real-time data collected from multi-source sensors, the model parameters are continuously calibrated, significantly improving the accuracy of temperature and humidity control. Furthermore, by acquiring actual data in real time and leveraging the rapid simulation capabilities of the digital twin model, environmental change trends can be predicted in a short time, allowing for proactive control decisions and effectively enhancing the system's real-time performance and dynamic response capabilities.

[0021] It should be understood that the descriptions of technical features, technical solutions, beneficial effects, or similar language in this application do not imply that all features and advantages can be achieved in any single embodiment. Rather, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution, or beneficial effect is included in at least one embodiment. Therefore, the descriptions of technical features, technical solutions, or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions, and beneficial effects described in this embodiment can be combined in any suitable manner. Those skilled in the art will understand that embodiments can be implemented without one or more specific technical features, technical solutions, or beneficial effects of a particular embodiment. In other embodiments, additional technical features and beneficial effects may be identified in specific embodiments that do not embody all embodiments. Attached Figure Description

[0022] Figure 1 A system architecture diagram of a cleanroom temperature and humidity intelligent control system based on digital twin provided for embodiments of this application; Figure 2 A planning example diagram of a constant temperature and humidity cleanroom provided for embodiments of this application; Figure 3 A schematic diagram illustrating the principle of a PLC device insertion loss test provided in an embodiment of this application; Figure 4 A schematic diagram illustrating the principle of a PLC device directionality test provided in an embodiment of this application; Figure 5 A schematic diagram illustrating the principle of PLC device operating bandwidth testing provided in this application embodiment; Figure 6A schematic diagram illustrating the principle of a polarization-dependent loss test for a PLC device, provided in an embodiment of this application; Figure 7 A schematic diagram illustrating the principle of a PLC device return loss test provided in an embodiment of this application; Figure 8 A flowchart illustrating a method for intelligent control of cleanroom temperature and humidity based on digital twins, provided for an embodiment of this application; Figure 9 A flowchart illustrating another method for intelligent control of cleanroom temperature and humidity based on digital twins, provided in an embodiment of this application; Figure 10 A flowchart illustrating another method for intelligent control of cleanroom temperature and humidity based on digital twins, provided in an embodiment of this application; Figure 11 A flowchart illustrating another method for intelligent control of cleanroom temperature and humidity based on digital twins, provided in an embodiment of this application; Figure 12 A flowchart illustrating another method for intelligent control of cleanroom temperature and humidity based on digital twins, provided in an embodiment of this application; Figure 13 A schematic diagram of the structure of a cleanroom temperature and humidity intelligent control device based on digital twin provided in this application embodiment; Figure 14 This is a schematic diagram of the hardware structure of a cleanroom temperature and humidity intelligent control device based on digital twin, provided in an embodiment of this application. Detailed Implementation

[0023] In the description of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. The "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Furthermore, "at least one" means one or more, and "multiple" means two or more. The terms "first," "second," etc., do not limit the quantity or order of execution, and "first," "second," etc., do not necessarily imply differences.

[0024] It should be noted that, in this application, the terms "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or illustration. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0025] The intelligent control method for cleanroom temperature and humidity based on digital twins provided in this application embodiment can be applied to a cleanroom temperature and humidity intelligent control system 100 based on digital twins, such as... Figure 1 As shown, the cleanroom temperature and humidity intelligent control system 100 based on digital twins includes: a model building module 101, a multi-source data acquisition module 102, and an intelligent control module 103.

[0026] The intelligent control module 103 is connected to the model building module 101 and the multi-source data acquisition module 102, respectively.

[0027] This digital twin-based intelligent temperature and humidity control system 100 for cleanrooms can be applied to the testing and inspection process in constant temperature and humidity cleanrooms. This process includes: test site construction, test system setup, and test method development. This constant temperature and humidity cleanroom can be used to develop testing capabilities for optical device products (fiber optic connectors, optical splitters, etc.), breaking through the technical requirements of ±1℃, ±2%RH constant temperature and humidity environment and 100,000-level cleanliness for optical device products (fiber optic connectors, optical splitters, etc.). It can also be continuously updated for testing capabilities of products such as cables, paper, and wood.

[0028] For example, such as Figure 2 As shown, the total area of ​​the constant temperature and humidity cleanroom laboratory is 104 square meters, including a buffer room (changing room), a machine room, a constant temperature and humidity room (about 35 square meters) and a cleanroom (about 35 square meters).

[0029] Figure 2 The temperature and humidity control room is designed according to the laboratory layout requirements. It is recommended that the area of ​​a single room be 30-50㎡ (which can be adjusted according to actual needs). It is divided into a main experimental area (the core temperature and humidity control area), an equipment room (to house the precision air conditioning unit and control system), and a transition buffer zone (to reduce external environmental interference).

[0030] The temperature in the constant temperature and humidity chamber is maintained at 23℃±1℃ (constant throughout the year), using a precision air conditioning unit (customized model, equipped with an 8-channel recorder for real-time monitoring). Humidity is controlled at 50%±2%, equipped with an independent humidification / dehumidification system (integrated into the air conditioning unit).

[0031] The walls of the constant temperature and humidity room are constructed using 50mm thick rock wool corrugated steel panels (double-sided 0.426mm galvanized steel plates, rock wool density ≥120kg / m³), possessing Class A fire resistance and thermal insulation properties (thermal conductivity ≤0.043W / m·K). Joints are sealed tightly with Dow Corning sealant. The ceiling is constructed using 50mm thick magnesium oxide corrugated steel panels (fire resistance Class A1), concealing air conditioning ducts and high-efficiency filters. The floor is made of 2mm thick PVC anti-static flooring (surface resistivity 10^6-10^9Ω), with hot-melt welded joints and dust-free treatment. The base layer is self-leveling cement (flatness ≤2mm / 2m), with a load-bearing capacity ≥500kg / m². The corrugated steel panels are complemented by rounded-corner aluminum skirting boards, 120mm high, seamlessly integrated with the floor.

[0032] The constant temperature and humidity chamber is equipped with an air supply system: an aluminum alloy air supply perforated plate (uniformly distributed), combined with a high-efficiency filter (Q=1000M3 / H) to ensure airflow uniformity; an electrical system: an independent power distribution control box; lighting uses 48W embedded LED lights (shadowless design, illuminance ≥300lux); and a monitoring system: an 8-channel temperature and humidity recorder (real-time data storage, abnormal alarm function).

[0033] Figure 2 Medium-sized cleanrooms are 30-50㎡ per room (including equipment area and operating area), and the cleanliness level meets ISO Class 8 (Class 100,000).

[0034] The cleanroom walls are constructed using 50mm thick rock wool corrugated steel panels (electrostatically powder-coated for easy cleaning), with rounded corners to reduce dust accumulation. The ceiling system uses magnesium oxide corrugated steel panels (including ceiling hangers and angle iron supports), with high-efficiency air vents (Q=500 / 1000M3 / H) and FFU units installed at the top. Doors and windows are steel airtight doors (with door closers), and the windows are double-glazed tempered glass with tightly sealed rubber strips around the perimeter. The flooring is made of 2mm thick PVC homogeneous membrane (T-grade wear resistance, R10 anti-slip coefficient), seamlessly welded. Concealed stainless steel floor drains (with water seals) are used, with a drainage slope ≥0.5%.

[0035] The cleanroom is equipped with a supply and exhaust ventilation system: galvanized steel sheet ducts (δ0.5-1.0mm, fabricated on-site), and matching fire dampers (70℃ fusion cutoff) and air volume regulating valves (320). The cleanroom is equipped with a 250mm diameter filter and a three-stage filtration system consisting of a pre-filter (G4), a medium-efficiency filter (F8), and a high-efficiency filter (H13), with an air exchange rate of ≥20 times / hour. A differential pressure control system ensures a pressure difference of ≥10Pa between the buffer room and the main clean area, regulated by a differential pressure sensor linked to the air valve. The cleanroom also features a lighting system with ceiling-mounted LED lights (48W / 36W, IP65 protection) providing ≥400 lux of illumination. Cleaning facilities include stainless steel cleaning tool cabinets on the walls and pre-installed charging points for cleaning equipment on the floor.

[0036] Figure 2 The buffer zone is recommended to be 10 square meters, divided into a changing area (5 square meters) and a shoe-changing area (5 square meters). The flow of people should be designed in a one-way direction (entrance, shoe changing, changing clothes, clean area) to avoid cross-contamination.

[0037] The buffer room walls are constructed with 50mm thick rock wool corrugated steel panels (with an antibacterial coating), and the corners are rounded. The ceiling is made of magnesium oxide corrugated steel (matching the cleanroom), with recessed LED lighting. The floor is 2mm thick PVC wear-resistant flooring (anti-slip texture, resistant to chemical corrosion), with colors distinguishing functional areas. A stainless steel threshold connects the flooring to the cleanroom, with a height difference of ≤3mm. The lockers within the buffer room are made of 304 stainless steel (double-layer hanging space + storage compartments), and are 900mm in size. 450 1800mm; the shoe changing stool uses a stainless steel frame and PP material seat (embedded design, fixed against the wall); the intelligent access control uses a card swipe or fingerprint recognition system (linked to the cleanroom differential pressure control).

[0038] The buffer room is equipped with a ventilation system: independent exhaust vents (with primary and secondary filters), air exchange rate ≥ 8 times / hour; lighting design: 36W ceiling-mounted purification LED light (color temperature 4000K), illuminance ≥ 200 lux.

[0039] Figure 2 The central computer room is used to house key components and control equipment of the air conditioning system, taking into full account the heat dissipation of the equipment, maintenance space and ease of operation for personnel.

[0040] If the constant temperature and humidity cleanroom is used to test optical device products, the physical equipment inside the cleanroom may include: light source, broadband light source, filter module unit, optical power meter, polarization controller, spectrum analyzer, temporary contact, high power light source, return loss tester, etc.

[0041] The testing methods may include the following: insertion loss test, directivity test, channel uniformity test, test of the operating bandwidth of the programmable logic controller (PLC) component, test of polarization-dependent loss, and return loss test.

[0042] Among them, the insertion loss test is as follows: Figure 3 As shown in Figure a, perform the test according to the device shown in Figure a, and record the output optical power Po of the i-th output port. Where L is the length of the input pigtail and L2 is the length of the output pigtail. As shown in Figure b, cut the device pigtail at point A to the right of the temporary junction. The distance L between the temporary junction and point A should be no less than 30cm. As shown in Figure c, remove the PLC device from the test device, prepare the fiber end face at the cut point, and couple the fiber end face to the detection unit. Then measure and record the input optical power P. Calculate the insertion loss of the relevant ports.

[0043] Directional tests, such as Figure 4 As shown in Figure a, firstly, the test system is zeroed. Next, the output fiber end face of the filter unit is prepared, ensuring good coupling between the fiber end face and the detection unit. Then, the input optical power P is measured and recorded. Next, as shown in Figure b, the pigtail behind the filter unit is fused to port i of the device under test, and this port is connected to the power meter. Then, the output optical power P' of port j of the device under test is measured and recorded. Finally, the directivity of the relevant ports is calculated.

[0044] Channel uniformity testing involves measuring the insertion loss at each output port of the PLC optical splitter under the input wavelength condition. The difference between the maximum and minimum values ​​represents the channel uniformity of the device. For tests conducted at multiple wavelengths, the maximum value is selected as the channel uniformity of the device under test.

[0045] Testing the operating bandwidth of PLC components, such as Figure 5 As shown, preheat all active components (broadband light source, spectrometer). After the active components stabilize, first directly connect the broadband light source and spectrometer, and store the spectral curve P1 in the spectral region involved in the test of each sample. The test conditions can use a resolution of 1 nm / division or 10 nm / division, and the start and end wavelengths should exactly cover the specified passband width. Figure 5 Connect the test system, ensuring that segments F1, F2, and F3 use the same type of fiber. Use a spectrometer to scan the selected spectral region to obtain the spectral curve P2. Execute the P2-P1 function in the spectrometer to obtain the spectral characteristics of the insertion loss of the test sample as a function of wavelength. Record the insertion loss of the sample.

[0046] Testing of polarization-dependent loss, such as Figure 6 As shown, connect the test system and turn on the system preheating; set the wavelength scanning range of the wavelength-tunable light source and the polarization state change of the polarization controller; initialize each channel of the system; connect the optical splitter of the PLC under test, and after stabilization, perform scanning and export the data.

[0047] Return loss test, such as Figure 7 As shown in Figure a, select the channel wavelength to be tested and connect the test pigtail to the return loss tester. Note that the connector type B of the test pigtail should be consistent with the connector type of the return loss tester. After connection, use a round rod with a diameter no greater than 5 mm to wrap at least 5 turns around the end of the pigtail for calibration of the return loss tester. Next, as shown in Figure b, connect the PLC device to the test pigtail. On the other end of the PLC device under test, use a round rod with a diameter no greater than 5 mm to wrap at least 5 turns around the pigtail at all ports. Then, record the test result; this result is the return loss value.

[0048] To address the technical challenges of real-time performance and lag in dynamic response of cleanroom temperature and humidity control in existing technologies, this application provides a digital twin-based intelligent control method for cleanroom temperature and humidity. This method constructs a digital twin model simulating the temperature, humidity distribution, and airflow conditions within a cleanroom, achieving millimeter-level precision simulation of the cleanroom environment. By combining real-time data from multi-source sensors and continuously calibrating model parameters, the accuracy of temperature and humidity control is significantly improved. Furthermore, by acquiring real-time actual data and leveraging the rapid simulation capabilities of the digital twin model, environmental change trends can be predicted in a short time, allowing for proactive control decisions and effectively enhancing the system's real-time performance and dynamic response capabilities.

[0049] like Figure 8 As shown in the embodiments of this application, the intelligent control method for cleanroom temperature and humidity based on digital twins includes: S801. Construct a digital twin model simulating the temperature and humidity distribution and airflow conditions in a clean room.

[0050] In some implementations, a device heat dissipation submodule can be added to the model. By embedding the power parameters of detection devices such as lasers and spectrometers, the impact of local heat load on temperature and humidity during operation can be simulated.

[0051] S802: Real-time data of the cleanroom is collected in real time through multi-source sensors.

[0052] Among them, the multi-source sensor includes at least multiple high-precision temperature and humidity sensors.

[0053] In some implementations, an 8-channel temperature and humidity recorder is used to collect temperature and humidity data in the core area (main experimental area of ​​the constant temperature and humidity room and clean room operating area), and simultaneously access data from the air volume sensor of the supply and exhaust system, the operating current of the air conditioning unit, the differential pressure sensor of the filter, etc., to achieve high-frequency acquisition once per second.

[0054] In some implementations, the deployment density of multiple high-precision temperature and humidity sensors is greater than the preset density; multi-source sensors also include laser particle counters and infrared thermal imagers. Adding miniature temperature and humidity sensors (one per 5㎡) to key areas (such as around the optical device testing station) and introducing infrared thermal imagers to capture heat dissipation hotspots of the equipment can improve the simulation accuracy of the digital twin model for local temperature and humidity fields.

[0055] In some implementations, the deployment of data acquisition points may include: using an 8-channel temperature and humidity recorder to collect real-time temperature and humidity data of the main experimental area of ​​the constant temperature and humidity chamber and the cleanroom operating area (sampling frequency 1 time / minute); accessing precision air conditioning operating parameters (compressor frequency, supply air temperature), humidification / dehumidification system operating status (humidification capacity, dehumidification efficiency), and supply and exhaust air system data (fan speed, air valve opening, filter pressure difference); recording the number of personnel entering and exiting through the buffer room intelligent access control system (affecting the cleanroom pressure difference); and capturing instantaneous heat load through the operating status signals of detection equipment (such as lasers, spectrometers).

[0056] S803. By comparing the actual data with the first simulation value of the digital twin model for the first moment, the parameters of the digital twin model are calibrated.

[0057] In some implementations, noise reduction is performed on the original data through edge computing nodes (such as Kalman filtering to process temperature and humidity fluctuations), and the results are compared with the simulation results of the digital twin model to correct the model parameters (such as reverse calibration of the air conditioner heating efficiency parameters when the actual temperature deviation exceeds 0.5℃) to ensure the consistency between the virtual model and the physical entity.

[0058] S804. Input the actual data into the digital twin model to obtain the second simulation value of the digital twin model for the second time step.

[0059] S805: Based on the deviation between the second simulation value and the set standard value, output control commands to drive the physical device to execute.

[0060] In some implementations, the digital twin model simulates the effects of different control strategies (such as increasing the cooling power of the air conditioner and increasing the air supply volume) based on the current temperature and humidity data (such as the actual temperature of the constant temperature and humidity room being 24℃), and outputs the optimal command (such as lowering the air conditioner set temperature by 0.3℃) to drive the precision air conditioner and humidification / dehumidification system to execute, shortening the control response time to less than 30 seconds (better than the 5-10 minutes of traditional threshold control).

[0061] In some implementations, in response to sudden disturbances such as personnel entering the buffer room or equipment overheating, the model predicts the temperature and humidity fluctuation trend 5 minutes in advance (e.g., personnel entering the clean room causes a 1% increase in humidity), and pre-adjusts the air supply volume or dehumidification intensity to maintain the parameters stable within ±0.5℃ / ±1%RH.

[0062] By combining optical device testing methods (such as insertion loss testing and polarization-dependent loss testing), the thermal load (such as laser heat dissipation) of the testing equipment during operation is simulated in the model, and the temperature and humidity control strategy is adjusted in advance to ensure that the environmental parameters are stable during the testing process (such as temperature fluctuation of the constant temperature and humidity chamber ≤0.3℃ during the test).

[0063] Based on the above technical solution, the intelligent control method for cleanroom temperature and humidity based on digital twins provided in this application achieves millimeter-level precision simulation of the cleanroom environment by constructing a digital twin model that simulates the temperature and humidity distribution and airflow state within the cleanroom. By combining real-time data collected from multi-source sensors and continuously calibrating the model parameters, the accuracy of temperature and humidity control is significantly improved. Furthermore, by collecting actual data in real time and combining it with the rapid simulation capabilities of the digital twin model, environmental change trends can be predicted in a short time, allowing for proactive control decisions and effectively enhancing the system's real-time performance and dynamic response capabilities.

[0064] In one possible implementation, combining Figure 8 ,like Figure 9 As shown, the method of S801 above specifically includes the following implementations S901 to S902, which are described in detail below: S901. Based on the physical layout of the cleanroom, construct a geometric model.

[0065] In some implementation methods, based on the laboratory planning map (such as a constant temperature and humidity room of 33.29㎡ and a clean room of 35.05㎡), the structural details of rock wool color steel plate walls, sulfur-oxygen magnesium color steel plate ceilings, and PVC anti-static flooring are restored through building information modeling (BIM) technology, and the spatial location and connection relationship of equipment such as air outlets (aluminum alloy air outlet plates), high-efficiency filters (Q=1000M³ / H), and precision air conditioning units are accurately mapped.

[0066] S902. Incorporate physical property equations to establish the correlation between equipment operating parameters and temperature, humidity, and airflow fields.

[0067] In some implementations, temperature and humidity control equations (such as energy conservation and humidity transfer equations) and airflow organization models (based on the air pressure-air volume relationship of the supply and exhaust air system) are integrated to simulate the dynamic changes of the temperature and humidity field under different operating conditions (such as equipment start-up and shutdown, personnel entry); in response to the ISO 8 cleanroom requirements, a particle diffusion model is added to correlate the mapping relationship between the number of air changes (≥20 times / hour) and the cleanliness level.

[0068] Based on the above technical solutions, a digital twin model can be accurately constructed, providing a foundation for subsequent intelligent control of temperature and humidity.

[0069] In one possible implementation, combining Figure 9 ,like Figure 10 As shown, the above method also includes the following steps S1001 to S1002, which are described in detail below: S1001. Integrate a dual-objective reward function of temperature and humidity compliance rate and energy consumption in the digital twin model.

[0070] The formula for calculating the dual-objective reward function is as follows: ; It is a bi-objective reward function; Rewards will be given for meeting temperature and humidity standards; As an energy consumption reward; , The target weight coefficient is α+β=1; When the temperature and humidity deviation is within the preset range, the formula for calculating the temperature and humidity compliance bonus is as follows: ; Basic reward value; This is the deviation penalty coefficient; Temperature deviation; Humidity deviation; When the temperature and humidity deviation exceeds the preset range, the formula for calculating the temperature and humidity compliance bonus is as follows: ; This refers to the penalty coefficient for exceeding the limit; The formula for calculating energy consumption bonus is: ; Basic energy consumption bonus value; This is the energy consumption penalty coefficient. If the current total energy consumption exceeds the preset percentage of the rated maximum total energy consumption, the energy consumption reward will be negative.

[0071] One possible implementation is to adjust the target weight coefficient according to the cleanroom's operating scenario. Specifically, when the cleanroom's operating scenario is a testing operation, the target weight coefficient for temperature and humidity compliance rewards is increased, while the target weight coefficient for energy consumption rewards is decreased. When the cleanroom's operating scenario is not a testing operation, the target weight coefficient for temperature and humidity compliance rewards is decreased, while the target weight coefficient for energy consumption rewards is increased.

[0072] S1002. The digital twin model is pre-trained offline using a reinforcement learning algorithm, and then fine-tuned online in the cleanroom to ensure that the control commands meet the preset temperature and humidity compliance thresholds and energy consumption reduction thresholds.

[0073] Based on the above technical solution, reinforcement learning algorithms are introduced into the model to train intelligent control strategies with temperature and humidity compliance rate and energy consumption as dual objectives. For example, during off-peak periods at night, the air conditioning load is automatically reduced, and the environment is maintained through energy storage devices, which is expected to reduce the total energy consumption of the computer room.

[0074] In one possible implementation, combining Figure 8 ,like Figure 11 As shown, the above method also includes the following steps S1101 to S1104, which are described in detail below: S1101. Collect the equipment operating parameters of the physical equipment in the clean room at the first moment.

[0075] In some implementations, the equipment operating parameters include those of precision air conditioners, humidification / dehumidification systems, fans, etc., such as air conditioner power and humidifier capacity.

[0076] S1102. By comparing the equipment operating parameters with the first predicted operating parameters of the physical equipment at the first moment in the digital twin model, the equipment performance degradation factor is corrected so that the degradation state of the digital twin model and the physical equipment are consistent.

[0077] S1103. Input the equipment operating parameters into the digital twin model to obtain the second predicted operating parameters of the digital twin model for the physical equipment at the second time.

[0078] S1104. Based on the second predicted operating parameters, predict the performance degradation trend and remaining lifespan of the physical equipment, and generate early warning information and maintenance suggestions.

[0079] In some implementations, for short-term predictions, performance degradation curves of physical devices can be constructed, such as a model of filter resistance changing over time. For long-term predictions, deep learning networks can be used to train the predictive operating parameters output by the digital twin model, so that the trained deep learning network outputs performance degradation trends and remaining lifetime.

[0080] For example, when the filter differential pressure exceeds 50% of the initial value (indicating blockage), the model predicts the remaining service life (e.g., 30 days) and generates a maintenance work order; through model simulation of the fan vibration frequency, the risk of bearing wear is warned in advance (e.g., when the vibration amplitude exceeds 0.1mm, maintenance is triggered).

[0081] Based on the above technical solution, the remaining lifespan of the equipment can be predicted by analyzing data such as fan vibration and filter pressure difference using a digital twin model (e.g., issuing a replacement warning 30 days before filter blockage), thus avoiding uncontrolled temperature and humidity due to equipment failure.

[0082] In one possible implementation of the embodiments of this application, combined with Figure 8 ,like Figure 12 As shown, the above method may also include the following steps S1201 to S1202, which are described in detail below: S1201. Set temperature and humidity requirements for various application scenarios in the digital twin model.

[0083] S1202. If the application scenario of the cleanroom changes, adjust the digital twin model according to the temperature and humidity requirements of the corresponding scenario.

[0084] Based on the above technical solution, the environmental parameter requirements for different product testing are preset in the model (such as humidity for paper testing), and a scene switching module is established. When the testing object changes from optical devices to paper, the simulation model of the corresponding scene is automatically called (such as adjusting the air supply volume and humidification strategy), reducing the time for manual readjustment.

[0085] The above primarily describes the solutions of the embodiments of this application from the perspective of device implementation. It is understood that each device, such as a digital twin-based intelligent control device for cleanroom temperature and humidity, includes at least one of the hardware structures and software modules corresponding to each function in order to achieve the above-mentioned functions. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0086] This application embodiment can divide the functional units of the cleanroom temperature and humidity intelligent control device based on digital twins according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or software functional units. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0087] When using integrated units, Figure 13 A possible structural schematic diagram of the cleanroom temperature and humidity intelligent control device 1300 based on digital twin involved in the above embodiments is shown. The cleanroom temperature and humidity intelligent control device 1300 based on digital twin includes a processing unit 1301 and a communication unit 1302, and may also include a storage unit 1303. Figure 13 The structural diagram shown can be used to illustrate the structure of the cleanroom temperature and humidity intelligent control device based on digital twin involved in the above embodiments.

[0088] when Figure 13 The schematic diagram shown illustrates the structure of the intelligent control device for cleanroom temperature and humidity based on digital twins involved in the above embodiments. The processing unit 1301 is used to control and manage the operation of the intelligent control device for cleanroom temperature and humidity based on digital twins. The communication unit 1302 is used for the intelligent control device for cleanroom temperature and humidity based on digital twins to communicate with other devices. The storage unit 1303 is used to store the program code and data of the intelligent control device for cleanroom temperature and humidity based on digital twins.

[0089] For example, processing unit 1301 and communication unit 1302; Processing unit 1301 is used to construct a digital twin model simulating the temperature and humidity distribution and airflow conditions in a clean room.

[0090] The processing unit 1301 is also used to collect real-time data of the cleanroom at the first moment through multi-source sensors; the multi-source sensors include at least a number of high-precision temperature and humidity sensors.

[0091] The processing unit 1301 is also used to calibrate the parameters of the digital twin model by comparing the actual data with the first simulation value of the digital twin model for the first moment.

[0092] The processing unit 1301 is also used to input actual data into the digital twin model to obtain the second simulation value of the digital twin model for the second time step.

[0093] The communication unit 1302 is used to output control commands based on the deviation between the second simulation value and the set standard value, and drive the physical device to execute.

[0094] In one possible implementation, the processing unit 1301 is specifically used to construct a geometric model based on the physical layout of the cleanroom; and to incorporate physical characteristic equations to establish the correlation between equipment operating parameters and temperature and humidity fields and airflow fields.

[0095] In one possible implementation, the processing unit 1301 is also used to integrate a dual-objective reward function of temperature and humidity compliance rate and energy consumption in the digital twin model; to perform offline pre-training in the digital twin model through a reinforcement learning algorithm, and then to perform online fine-tuning in the clean room so that the control commands meet the preset temperature and humidity compliance rate threshold and energy consumption reduction threshold.

[0096] In one possible implementation, the processing unit 1301 is further configured to adjust the target weight coefficient according to the operating scenario of the cleanroom; when the operating scenario of the cleanroom is a testing operation, the target weight coefficient of the temperature and humidity compliance reward is increased and the target weight coefficient of the energy consumption reward is decreased; when the operating scenario of the cleanroom is a non-testing operation, the target weight coefficient of the temperature and humidity compliance reward is decreased and the target weight coefficient of the energy consumption reward is increased.

[0097] In one possible implementation, the processing unit 1301 is further configured to collect the equipment operating parameters of the physical equipment in the cleanroom at a first moment; by comparing the equipment operating parameters with the first predicted operating parameters of the physical equipment in the digital twin model at the first moment, the equipment performance degradation factor is corrected to ensure that the degradation state of the digital twin model and the physical equipment is consistent; the equipment operating parameters are input into the digital twin model to obtain the second predicted operating parameters of the physical equipment in the digital twin model at a second moment; based on the second predicted operating parameters, the performance degradation trend and remaining lifespan of the physical equipment are predicted, and early warning information and maintenance suggestions are generated.

[0098] In one possible implementation, the processing unit 1301 is specifically used to construct the performance degradation curve of the physical device; or, through a deep learning network, the predicted operating parameters output by the digital twin model are trained so that the trained deep learning network outputs the performance degradation trend and remaining lifetime.

[0099] In one possible implementation, the processing unit 1301 is also used to set temperature and humidity requirements for various application scenarios in the digital twin model; if the application scenario of the cleanroom changes, the digital twin model is adjusted according to the temperature and humidity requirements of the corresponding scenario.

[0100] The processing unit 1301 can be a processor or a controller, and the communication unit 1302 can be a communication interface, transceiver, transceiver circuit, transceiver device, etc. The term "communication interface" is a general term and may include one or more interfaces. The storage unit 1303 can be a memory. When the cleanroom temperature and humidity intelligent control device 1300 based on digital twins is a chip, the processing unit 1301 can be a processor or a controller, and the communication unit 1302 can be an input interface and / or an output interface, pins, or circuits, etc. The storage unit 1303 can be a storage unit within the chip (e.g., a register, cache, etc.) or a storage unit located outside the chip (e.g., read-only memory (ROM), random access memory (RAM, etc.).

[0101] Figure 13If the integrated units in the process are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. Storage media for storing computer software products include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks.

[0102] Figure 13 The units in the process can also be called modules; for example, a processing unit can be called a processing module.

[0103] This application also provides a hardware structure diagram of a cleanroom temperature and humidity intelligent control device based on digital twins, see [link / reference]. Figure 14 The cleanroom temperature and humidity intelligent control device 1400 based on digital twin includes a processor 1401, and optionally, a memory 1402 connected to the processor 1401.

[0104] In the first possible implementation, see Figure 14 The cleanroom temperature and humidity intelligent control device 1400 based on digital twins also includes a transceiver 1403. The processor 1401, memory 1402, and transceiver 1403 are connected via a bus. The transceiver 1403 is used to communicate with other devices or communication networks. Optionally, the transceiver 1403 may include a transmitter and a receiver. The device in the transceiver 1403 used to implement the receiving function can be considered as a receiver, which is used to perform the receiving steps in the embodiments of this application. The device in the transceiver 1403 used to implement the transmitting function can be considered as a transmitter, which is used to perform the transmitting steps in the embodiments of this application.

[0105] Based on the first possible implementation method Figure 14 The structural diagram shown can be used to illustrate the structure of the cleanroom temperature and humidity intelligent control device based on digital twin involved in the above embodiments.

[0106] in, Figure 14 This can also be illustrated by the system chip in a cleanroom temperature and humidity intelligent control device based on digital twins. In this case, the actions performed by the aforementioned cleanroom temperature and humidity intelligent control device based on digital twins can be implemented by this system chip. The specific actions performed can be found above and will not be repeated here.

[0107] In implementation, each step of the method provided in this embodiment can be completed by integrated logic circuits in the processor or by instructions in software form. The steps of the method disclosed in the embodiments of this application can be directly manifested as being executed by a hardware processor, or being executed by a combination of hardware and software modules in the processor.

[0108] The processor in this application may include, but is not limited to, at least one of the following: a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a microcontroller unit (MCU), or an artificial intelligence processor, etc., which are various computing devices that run software. Each computing device may include one or more cores for executing software instructions to perform calculations or processing. The processor may be a separate semiconductor chip or integrated with other circuits into a single semiconductor chip. For example, it may be integrated with other circuits (such as encoding / decoding circuits, hardware acceleration circuits, or various bus and interface circuits) to form a System-on-a-Chip (SoC), or it may be integrated as a built-in processor within an ASIC. The ASIC with the integrated processor may be packaged separately or together with other circuits. In addition to the cores for executing software instructions to perform calculations or processing, the processor may further include necessary hardware accelerators, such as field-programmable gate arrays (FPGAs), PLDs (programmable logic devices), or logic circuits that implement dedicated logic operations.

[0109] The memory in the embodiments of this application may include at least one of the following types: read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions; random access memory (RAM) or other types of dynamic storage devices capable of storing information and instructions; or electrically erasable programmable read-only memory (EEPROM). In some scenarios, the memory may also be a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0110] This application also provides a computer-readable storage medium including instructions that, when run on a computer, cause the computer to perform any of the methods described above.

[0111] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to perform any of the methods described above.

[0112] This application also provides a chip including a processor and an interface circuit. The interface circuit is coupled to the processor. The processor is used to run computer programs or instructions to implement the above-described method. The interface circuit is used to communicate with other modules outside the chip.

[0113] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks (SSDs)).

[0114] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0115] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of this application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.

Claims

1. A method for intelligent control of cleanroom temperature and humidity based on digital twins, characterized in that, include: Construct a digital twin model simulating the temperature and humidity distribution and airflow conditions within a cleanroom; The cleanroom's actual data is collected in real time at the first moment using multi-source sensors; the multi-source sensors include at least a number of high-precision temperature and humidity sensors. The parameters of the digital twin model are calibrated by comparing the actual data with the first simulation value of the digital twin model at the first moment. The actual data is input into the digital twin model to obtain the second simulation value of the digital twin model for the second time point; Based on the deviation between the second simulation value and the set standard value, a control command is output to drive the physical device to execute.

2. The method according to claim 1, characterized in that, The construction of a digital twin model simulating the temperature and humidity distribution and airflow conditions within a cleanroom includes: Based on the physical layout of the cleanroom, a geometric model is constructed; By incorporating physical property equations, the correlation between equipment operating parameters and temperature, humidity, and airflow fields is established.

3. The method according to claim 2, characterized in that, Also includes: The digital twin model incorporates a dual-objective reward function that integrates temperature and humidity compliance rates with energy consumption. The digital twin model is pre-trained offline using a reinforcement learning algorithm, and then fine-tuned online in the cleanroom to ensure that the control commands meet preset thresholds for temperature and humidity compliance and energy consumption reduction.

4. The method according to claim 3, characterized in that, The formula for calculating the dual-objective reward function is as follows: ; Let the bi-objective reward function be defined. Rewards will be given for meeting temperature and humidity standards; As an energy consumption reward; , The target weight coefficient is α+β=1; When the temperature and humidity deviation is within the preset range, the calculation formula for the temperature and humidity compliance reward is as follows: ； Basic reward value; This is the deviation penalty coefficient; Temperature deviation; Humidity deviation; When the temperature and humidity deviation exceeds the preset range, the calculation formula for the temperature and humidity compliance reward is as follows: ； This refers to the penalty coefficient for exceeding the limit; The formula for calculating the energy consumption reward is as follows: ； Basic energy consumption bonus value; The energy consumption penalty coefficient is used to determine the energy consumption reward. If the current total energy consumption exceeds the preset percentage of the rated maximum total energy consumption, the energy consumption reward will be negative.

5. The method according to claim 4, characterized in that, Also includes: Adjust the target weight coefficient according to the operating scenario of the cleanroom; When the cleanroom is used for testing, the target weighting coefficient for the temperature and humidity compliance reward is increased, and the target weighting coefficient for the energy consumption reward is decreased. When the cleanroom is not in a testing operation scenario, the target weight coefficient for the temperature and humidity compliance reward is reduced, and the target weight coefficient for the energy consumption reward is increased.

6. The method according to claim 1, characterized in that, Also includes: Collect the equipment operating parameters of the physical equipment in the cleanroom at the first moment; By comparing the device operating parameters with the first predicted operating parameters of the digital twin model for the physical device at the first moment, the device performance degradation factor is corrected so that the degradation state of the digital twin model is consistent with that of the physical device. The device operating parameters are input into the digital twin model to obtain the second predicted operating parameters of the digital twin model for the physical device at the second time. Based on the second predicted operating parameters, the performance degradation trend and remaining lifespan of the physical equipment are predicted, and early warning information and maintenance suggestions are generated.

7. The method according to claim 6, characterized in that, The step of predicting the performance degradation trend and remaining lifespan of the physical equipment based on the second predicted operating parameters includes: Construct the performance degradation curve of the physical device; or, The predicted operating parameters output by the digital twin model are trained using a deep learning network, so that the trained deep learning network outputs the performance degradation trend and remaining lifetime.

8. The method according to claim 1, characterized in that, The deployment density of the multiple high-precision temperature and humidity sensors is greater than the preset density; the multi-source sensors also include: a laser particle counter and an infrared thermal imager.

9. The method according to claim 1, characterized in that, Also includes: The digital twin model sets temperature and humidity requirements for various application scenarios; If the application scenario of the cleanroom changes, the digital twin model will be adjusted according to the temperature and humidity requirements of the corresponding scenario.

10. A cleanroom temperature and humidity intelligent control system based on digital twins, characterized in that, include: Model building module, multi-source data acquisition module, and intelligent control module; The model building module is used to build a digital twin model that simulates the temperature and humidity distribution and airflow conditions in a clean room. The multi-source data acquisition module is used to acquire the actual data of the cleanroom in real time at the first moment through multi-source sensors; the multi-source sensors include at least a number of high-precision temperature and humidity sensors. The model building module is also used to calibrate the parameters of the digital twin model by comparing the actual data with the first simulation value of the digital twin model for the first moment; The intelligent control module is used to input the actual data into the digital twin model to obtain the second simulation value of the digital twin model for the second time point; The intelligent control module is also used to output control commands based on the deviation between the second simulation value and the set standard value, and drive the physical device to execute.

Images