Multi-physics linkage control method, device and equipment and computer readable medium

Abstract

Embodiments of the present disclosure disclose a multi-physical field linkage control method, device, equipment and computer readable medium. A specific embodiment of the method comprises: collecting a set of multi-physical field environment parameters through an Internet of Things sensor network; determining a special sealing coating material, and querying the special sealing coating material to obtain a set of environmental threshold values; determining an initial solidification time prediction value, and correcting the initial solidification time prediction value to obtain a corrected solidification time prediction value; generating a set of device control parameters based on the corrected solidification time prediction value, the set of multi-physical field environment parameters and the set of environmental threshold values; and sending the set of device control parameters to a multi-physical field control device. The embodiment relates to the technical field of computers, and can avoid coating quality defects and device response lag.

Description

Technical Field

[0001] The embodiments disclosed herein relate to the field of computer technology, and more specifically to multiphysics linkage control methods, apparatuses, devices, and computer-readable media. Background Technology

[0002] Biosafety clean spaces (such as biosafety level 3 and above laboratories, vaccine bulk production workshops, and aseptic preparation filling workshops) have extremely high requirements for the temperature, humidity, air pressure gradient, and air cleanliness of the internal environment. During the construction or renovation of such spaces, it is necessary to apply special sealing coating materials (such as solvent-free epoxy sealing coatings or polyurethane antibacterial sealing coatings) to the walls, floors, and pipe penetration points to ensure the airtightness and resistance to microbial penetration.

[0003] Currently, the following technical problems exist in environmental control during the application of special coatings: The curing process of special sealing coatings is highly sensitive to temperature, humidity, air pressure, and volatile organic compound (VOC) concentrations. Current technical specifications in construction documentation, such as curing time and conditions, are fixed values ​​measured under standard environmental conditions at the factory. These parameters cannot be dynamically calibrated based on actual on-site temperature, humidity, air pressure gradients, and VOC concentrations. When actual environmental conditions deviate from standard conditions, if construction personnel continue to operate according to these fixed parameters, incomplete or over-curing of the coating can occur, leading to sealing failure, microbial penetration, and other quality defects.

[0004] In biological clean spaces, IoT sensor networks may experience communication interruptions, data drift, or data loss, leading to incomplete or unreliable multiphysics environmental parameter sets. This in turn prevents subsequent solidification degree prediction and multi-constraint dynamic parameter adjustment from being executed due to invalid input data, ultimately causing the control system to shut down.

[0005] The strong coupling effect between multi-physics field control devices causes repeated oscillations in environmental parameters, and the fixed environmental threshold cannot adapt to different stages of the coating curing process, resulting in low control accuracy, energy waste and coating quality risks.

[0006] The information disclosed in this background section is only intended to enhance the understanding of the background of the present disclosure concept, and therefore may contain information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0007] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0008] Some embodiments of this disclosure provide multiphysics linkage control methods, apparatuses, devices, and computer-readable media to solve one or more of the technical problems mentioned in the background section above.

[0009] In a first aspect, some embodiments of this disclosure provide a multi-physics field linkage control method for the construction of special coatings in biological clean spaces. The method includes: collecting a set of multi-physics field environmental parameters at a preset sampling period using an Internet of Things (IoT) sensor network deployed in the biological clean space; wherein the multi-physics field environmental parameters in the set include temperature, humidity, air pressure gradient, and volatile organic compound (VOC) concentration; determining a special sealing coating material based on the biological clean space; and querying the material constraint properties of the special sealing coating material to obtain an environmental threshold set, wherein the environmental threshold set includes a temperature threshold range, a humidity threshold upper limit, an air pressure gradient threshold range, and a VOC safety threshold; and based on the multi-physics field environmental parameters... The cumulative time after the coating application is completed is used to determine the initial curing time prediction. Based on the volatile organic compound (VOC) concentration and the VOC safety threshold, the initial curing time prediction is modified to obtain a corrected curing time prediction. Based on this corrected curing time prediction, the multi-physics environmental parameter set and the environmental threshold set are dynamically adjusted using multiple constraints to obtain an equipment control parameter set. This set includes a dynamic balance value sequence for airflow, a temperature control power sequence, a dehumidification power sequence, and a VOC purification power sequence. This equipment control parameter set is then sent to a multi-physics control device to control the temperature, humidity, air pressure gradient, and VOC concentration in the biological clean space.

[0010] Secondly, some embodiments of this disclosure provide a multi-physics field linkage control device for the construction of special coatings in biological clean spaces. The device includes: a data acquisition unit configured to acquire a set of multi-physics field environmental parameters according to a preset sampling period via an Internet of Things (IoT) sensor network deployed in the biological clean space, wherein the multi-physics field environmental parameters in the set include temperature, humidity, air pressure gradient, and volatile organic compound (VOC) concentration; a first determination unit configured to determine a special sealing coating material based on the biological clean space, and to perform material constraint property queries on the special sealing coating material to obtain an environmental threshold set, wherein the environmental threshold set includes a temperature threshold range, a humidity threshold upper limit, an air pressure gradient threshold range, and a VOC safety threshold; and a second determination unit configured to determine the multi-physics field environmental parameters according to the aforementioned multi-physics field environmental parameters. The system uses a set of environmental parameters and the cumulative time after coating application to determine the initial curing time prediction. Based on the volatile organic compound (VOC) concentration and the VOC safety threshold, it performs a hindrance correction on the initial curing time prediction to obtain a corrected curing time prediction. An adjustment unit is configured to perform multi-constraint dynamic parameter adjustment based on the corrected curing time prediction, the multi-physics environmental parameter set, and the environmental threshold set to obtain an equipment control parameter set. This set includes a dynamic balance value sequence for airflow, a temperature control power sequence, a dehumidification power sequence, and a VOC purification power sequence. A transmission unit is configured to transmit the equipment control parameter set to a multi-physics control device to control the temperature, humidity, air pressure gradient, and VOC concentration in the biological clean space.

[0011] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0012] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0013] The above-described embodiments of this disclosure have the following beneficial effects: Through the multi-physics field linkage control method for the construction of special coatings in biological clean spaces, as described in some embodiments of this disclosure, the methods achieve the following effects: real-time acquisition of multi-physics field environmental parameters, dynamic prediction and hindrance correction of curing time, adjustment of multiple constraint dynamic parameters, and collaborative control of multiple devices. These methods avoid quality defects such as incomplete or over-curing of the coating, eliminate the phenomenon of equipment response lagging behind environmental changes, and improve the system's fault tolerance in sensor failure scenarios. Specifically, the reason for incomplete or over-curing of the coating, leading to sealing failure, microbial penetration, and other quality defects, is that the curing process of special sealing coatings is highly sensitive to temperature, humidity, air pressure, and the concentration of volatile organic compounds. The curing time, curing conditions, and other process parameters in existing construction technical disclosure documents are fixed values ​​measured under standard environmental conditions at the time of manufacture, and cannot be dynamically calibrated according to the actual temperature, humidity, air pressure gradient, and volatile organic compound concentration at the construction site. When the actual environmental conditions deviate from the standard conditions, if construction personnel still operate according to the fixed process parameters, incomplete or over-curing of the coating will occur, leading to sealing failure, microbial penetration, and other quality defects. Based on this, the multi-physics linkage control method for special coating construction in biological clean spaces, as disclosed in some embodiments, firstly collects a set of multi-physics environmental parameters according to a preset sampling period through an Internet of Things (IoT) sensor network deployed in the biological clean space. This establishes a real-time data channel from the physical environment to the digital system, converting changes in temperature, humidity, air pressure gradient, and VOC concentration into a continuous data stream that can be processed by a computer, providing real-time and accurate input data for subsequent curing time prediction and multi-constraint dynamic parameter adjustment. Secondly, based on the aforementioned biological clean space, a special sealing coating material is determined, and its material constraint properties are queried to obtain an environmental threshold set. This allows for precise association between the current construction area and the specific coating material used, ensuring that subsequent threshold retrieval and parameter calculation target the correct material type, avoiding calculation errors caused by material confusion, and simultaneously obtaining the environmental parameter boundaries that allow construction with the material, providing a clear judgment standard for environmental compliance determination. Then, based on the aforementioned multiphysics environmental parameter set and the cumulative time after coating application, the predicted initial curing time is determined. Furthermore, based on the aforementioned volatile organic compound (VOC) concentration and VOC safety threshold, a hindrance correction is applied to the predicted initial curing time to obtain the corrected predicted curing time. Therefore, the remaining curing time required for the coating can be dynamically calculated based on real-time environmental parameters, ensuring that the process parameters in the construction technical briefing are matched with actual environmental conditions in real time. It also automatically extends the curing time when the VOC concentration exceeds the standard, avoiding incomplete curing due to unfavorable environmental conditions.Then, based on the aforementioned corrected curing time prediction, the aforementioned multiphysics environmental parameter set, and the aforementioned environmental threshold set, multi-constraint dynamic parameter adjustment is performed to obtain the equipment control parameter set. Thus, considering the cross-coupling effect between airflow, temperature, humidity, and VOC concentration, the environmental constraint boundaries can be dynamically adjusted according to the curing process. A global optimization algorithm is used to solve for the control sequence that minimizes the weighted sum of environmental deviation and energy consumption within several preset future control cycles, achieving coordinated control of multiple devices and fundamentally avoiding the oscillation problems and energy waste caused by single-cycle independent adjustment. Finally, the aforementioned equipment control parameter set is sent to the multiphysics control device to control the temperature, humidity, air pressure gradient, and volatile organic compound concentration of the aforementioned biological clean space. Thus, the optimized control commands can be accurately issued to each execution device, realizing a complete closed loop from environmental perception and dynamic calculation of process parameters to automatic equipment control. This implementation method achieves the technical effects of avoiding quality defects such as incomplete or over-cured coatings, eliminating the phenomenon of equipment response lagging behind environmental changes, and improving the system's fault tolerance in sensor failure scenarios. Attached Figure Description

[0014] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0015] Figure 1 This is a flowchart of some embodiments of the multi-physics field linkage control method for the construction of special coatings for biological clean spaces according to the present disclosure; Figure 2 This is a structural schematic diagram of some embodiments of the multi-physics field linkage control device for the construction of special coatings for biological clean spaces according to the present disclosure; Figure 3 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0016] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0017] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0018] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0019] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0020] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0021] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0022] refer to Figure 1 The flowchart 100 illustrates some embodiments of a multiphysics-based linkage control method, apparatus, electronic device, and computer-readable medium for the application of special coatings in biological clean spaces according to this disclosure. The multiphysics-based linkage control method for the application of special coatings in biological clean spaces includes the following steps: Step 101: Collect a set of multi-physics environmental parameters according to a preset sampling period by using an Internet of Things sensor network deployed in the biological clean space.

[0023] In some embodiments, the execution entity (e.g., a server) of the multi-physics field linkage control method for special coating construction in biological clean spaces can collect a set of multi-physics field environmental parameters at a preset sampling period through an Internet of Things (IoT) sensor network deployed in the biological clean space. The multi-physics field environmental parameters in the set may include: temperature, humidity, air pressure gradient, and volatile organic compound (VOC) concentration. The biological clean space can be any of the following: a biosafety level 3 or higher laboratory, a vaccine raw material production workshop, or a sterile preparation filling workshop. The IoT sensor network may include temperature and humidity sensors, air pressure sensors, and VOC sensors. As an example, the temperature and humidity sensor may be an industrial-grade wireless sensor using the SHT30 chip, model DS-1923 or a similar product. The air pressure sensor may be an air pressure sensor using the BMP388 chip, with a range of 300 hPa to 1100 hPa and an accuracy of ±0.2 hPa. The aforementioned volatile organic compound sensor can be a volatile organic compound sensor using an SGP40 chip, with a detection range of 0ppm to 1000ppm, expressed as toluene equivalent.

[0024] In some optional implementations of certain embodiments, the aforementioned execution entity may collect a set of multi-physics environmental parameters at a preset sampling period by means of an Internet of Things sensor network deployed in the biological clean space through the following steps: The first step is to control the aforementioned IoT sensor network to collect data according to a preset sampling period to obtain the original multiphysics environmental parameter set. The preset sampling period can be 60 seconds.

[0025] The second step involves filtering outliers from the original multiphysics environmental parameter set to obtain a new set of multiphysics environmental parameters. In practice, the executing entity removes multiphysics environmental parameters from the original set that exceed a preset reasonable range, thus obtaining the new set of multiphysics environmental parameters. The preset reasonable range can be: temperature 0℃~50℃, humidity 0%~100%RH, pressure gradient -50Pa~+50Pa (or absolute pressure 950hPa~1050hPa), and volatile organic compound concentration 0ppm~1000ppm (or 0mg / m³~2000mg / m³, in toluene equivalent).

[0026] In addressing the technical problems mentioned in the background section, the application scenario—specialized coating construction in biosafety clean spaces (such as biosafety level 3 and above laboratories, vaccine raw material production workshops, and aseptic preparation filling workshops), particularly in long-term, complex-environment, high-end biopharmaceutical base renovation projects or old P3 laboratory renovation projects—often presents the following technical challenges: IoT sensor networks within the biosafety clean space suffer from communication interruptions, data drift, or data loss, leading to incomplete or unreliable multiphysics environmental parameter sets. This, in turn, prevents subsequent curing degree prediction and multi-constraint dynamic parameter adjustment from executing due to invalid input data, ultimately causing control system interruption. Considering the following requirements of this application scenario: limited sensor deployment density and inconvenient maintenance, large impact range of a single sensor failure, and the inability to allow prolonged system downtime during construction, we have decided to adopt the following solution: In some alternative implementations of certain embodiments, the aforementioned implementing entity may collect a set of multi-physics environmental parameters at a preset sampling period by means of an Internet of Things sensor network deployed in the biological clean space through the following steps: The first step involves collecting an initial set of multiphysics environmental parameters at a preset sampling period using an IoT sensor network deployed in the aforementioned bio-clean space. These initial multiphysics environmental parameters include temperature, humidity, pressure gradient, and volatile organic compound concentration.

[0027] The second step involves real-time monitoring of the data stream status of each sensor in the aforementioned IoT sensor network to generate a sensor health status vector set. In practice, the executing entity can perform the following operations on each sensor in the IoT sensor network: send heartbeat packets to the sensor according to the preset sampling period. If no response packet is received from the sensor within a preset timeout period (e.g., 120 seconds), the online identifier of the sensor is set to "offline"; otherwise, the online identifier is set to "online". Simultaneously, if any field in the initial multiphysics environment parameter set has an empty value or is NaN, the data integrity identifier of the sensor is set to "incomplete"; otherwise, it is set to "complete". The sensor health status vector set includes the online identifier and data integrity identifier of each sensor. The data structure of the sensor health status vectors in the sensor health status vector set is in JSON format. As an example, the sensor health status vector can be represented as {"sensor_id": "TEMP_SENSOR_001", "online_flag": "online", "integrity_flag": "complete"}.

[0028] The third step involves real-time status detection of the aforementioned sensor health status vector set to obtain a sensor fault type code set. In practice, the aforementioned execution entity can perform real-time status detection on each sensor health status vector in the aforementioned sensor health status vector set and generate a sensor fault type code set according to the following rules: Rule 1: In response to the online identifier being "offline", a communication interruption code is generated. Rule 2: In response to the online identifier being "online" and the data integrity identifier being "incomplete", a data missing code is generated. Rule 3: In response to the online identifier being "online" and the data integrity identifier being "complete", the absolute value of the difference between the initial multiphysics environment parameter corresponding to the aforementioned sensor health status vector and the initial multiphysics environment parameter of the previous preset sampling period is determined, and in response to the above absolute value of the difference exceeding a preset drift threshold, a data drift code is generated; in response to the above absolute value of the difference not exceeding the above preset drift threshold, a normal code is generated. The sensor fault type codes in the aforementioned sensor fault type code set are one of the following: communication interruption code, data drift code, and data missing code. As an example, the aforementioned communication interruption code can be represented as "01". The missing data code can be represented as "03". The data drift code can be represented as "02". The normal code can be represented as "00". The sensor fault type code can be represented as {"sensor_id": "TEMP_SENSOR_001", "fault_code": "02"}. The preset drift thresholds can be temperature changes exceeding 5℃ / min, humidity changes exceeding 10%RH / min, air pressure changes exceeding 5Pa / min, or VOC concentration changes exceeding 200ppm / min. The sensor health state vector and the corresponding initial multiphysics environmental parameters have the same "sensor_id".

[0029] The fourth step involves performing an autoregressive time series prediction on the initial multiphysics environmental parameter set in response to the aforementioned sensor fault type code being a communication interruption code, to obtain the first compensation parameter. In practice, the execution entity can read the multiphysics environmental parameters of the sensor corresponding to the aforementioned sensor fault type code over the most recent N preset sampling periods in response to the aforementioned sensor fault type code being a communication interruption code, thus obtaining the target sensor environmental parameter sequence. Then, an autoregressive prediction method is used to predict the target sensor environmental parameter sequence forward to obtain the first compensation parameter. The aforementioned sensor fault type code and the corresponding sensor have the same "sensor_id". The aforementioned autoregressive prediction method is a statistical prediction method. This method analyzes the autocorrelation structure of historical data sequences and uses a linear combination of the observations from the previous N (e.g., N=5) time steps to predict the value at the next time step.

[0030] Fifth, in response to the aforementioned sensor fault type code being a data drift code, adaptive state correction is performed on the initial multiphysics environmental parameter set to obtain the second compensation parameter. In practice, the execution entity can, in response to the aforementioned sensor fault type code being a data drift code, read the multiphysics environmental parameters of the sensor corresponding to the aforementioned sensor fault type code in the most recent N preset sampling periods to obtain the target sensor environmental parameter sequence. Then, the aforementioned target sensor environmental parameter sequence is input into a Kalman filter to obtain the second compensation parameter. The observation noise covariance matrix of the aforementioned Kalman filter can be dynamically adjusted according to the value of the aforementioned data drift code, specifically as follows: using the aforementioned absolute difference value and sensor type as indices, the adjustment coefficient is retrieved from a preset noise covariance adjustment table, and the product of the aforementioned adjustment coefficient and the preset observation noise covariance matrix is ​​determined as the observation noise covariance matrix. The aforementioned preset noise covariance adjustment table can be a pre-calibrated two-dimensional lookup table. The row index of the aforementioned preset noise covariance adjustment table is the numerical range of the absolute difference value, the column index is the sensor type, and the table entries are dimensionless adjustment coefficients. The aforementioned preset observation noise covariance matrix can be a 4×4 diagonal matrix. The diagonal elements of this matrix represent the baseline observation noise variances of the temperature sensor, humidity sensor, barometric pressure sensor, and volatile organic compound sensor, respectively, while the off-diagonal elements are all 0. For example, the preset observation noise covariance matrix can be represented as: R_base = diag([0.01, 0.25, 0.04, 100]).

[0031] Step 6: In response to the aforementioned sensor fault type code being a missing data code, perform physical coupling parameter simulation on the initial multiphysics environment parameter set to obtain the third compensation parameter. In practice, the executing entity can, in response to the aforementioned sensor fault type code being a missing data code, use a multiple linear regression method, with the non-missing values ​​at the same sampling time in the initial multiphysics environment parameter set as independent variables, to determine the third compensation parameter. The non-missing values ​​can be values ​​in the initial multiphysics environment parameter set where the field value is not empty or not NaN. The aforementioned multiple linear regression method is a statistical modeling method. The regression coefficients of the aforementioned multiple linear regression method can be obtained by fitting the historically collected multiphysics environment parameter set using the least squares method.

[0032] Step 7: Based on the first compensation parameter, the second compensation parameter, and the third compensation parameter, the initial multiphysics environment parameter set is corrected to obtain a corrected multiphysics environment parameter set. In practice, the executing entity can replace the outliers or missing values ​​in the corresponding initial multiphysics environment parameters in the initial multiphysics environment parameter set with the first compensation parameter, the second compensation parameter, and the third compensation parameter to obtain the corrected multiphysics environment parameter set. As an example, in response to data drift of the temperature sensor "TEMP_SENSOR_001", the executing entity can replace the outliers in the initial multiphysics environment parameters of the temperature sensor "TEMP_SENSOR_001" with the second compensation parameter to obtain the corrected multiphysics environment parameters of the temperature sensor "TEMP_SENSOR_001".

[0033] Step 8: Perform a rationality check on the aforementioned modified multiphysics environment parameter set, obtain the check result, and, in response to the check result being deemed passed, determine the aforementioned modified multiphysics environment parameter set as a multiphysics environment parameter set. In practice, the executing entity can compare each modified multiphysics environment parameter in the aforementioned modified multiphysics environment parameter set with the aforementioned preset reasonable range to obtain the check result. In response to the check result being deemed passed, determine the aforementioned modified multiphysics environment parameter set as a multiphysics environment parameter set. As an example, in response to each modified multiphysics environment parameter not exceeding the aforementioned preset reasonable range, the check result can be deemed passed.

[0034] The aforementioned technical content and related content, as an inventive point of this disclosure, combined with "step 105," solves the technical problem that "in biological cleanrooms, IoT sensor networks experience communication interruptions, data drift, or data loss, leading to incomplete or unreliable multiphysics environmental parameter sets. This, in turn, prevents subsequent curing degree prediction and multi-constraint dynamic parameter adjustment from being executed due to invalid input data, ultimately causing control system interruption." Factors leading to control system interruption often include: IoT sensors in biological cleanrooms are exposed to harsh environments such as high cleanliness, strong ventilation, and residual chemical reagents for extended periods. Temperature and humidity sensors, air pressure sensors, and volatile organic compound sensors may experience power outages, communication module failures, sensitive element drift, or blockage by contaminants, leading to communication interruptions, data drift, or data loss. Once real-time data for a certain physical field is missing or abnormal, curing degree prediction, stagnation correction, and subsequent multi-constraint dynamic parameter adjustment, which rely on complete multiphysics environmental parameter sets, will all fail due to incomplete or unreliable input data. Current technologies typically only provide alarm signals and wait for manual intervention, lacking differentiated automatic compensation mechanisms for different types of sensor faults. This leads to system paralysis due to a single sensor failure, ultimately causing control system interruption. Addressing these issues can prevent control system interruptions caused by communication outages, data drift, or data loss. To achieve this, firstly, an IoT sensor network deployed in the bio-clean space collects initial multiphysics environmental parameter sets at preset sampling intervals. This establishes a real-time data channel from the physical environment to the digital system, converting changes in temperature, humidity, air pressure gradients, and VOC concentrations into a continuous data stream that can be processed by a computer. Secondly, the data stream status of each sensor in the IoT sensor network is monitored in real time to generate a sensor health status vector set. This allows for continuous tracking of the operating status of each sensor, enabling timely detection of abnormal events such as communication interruptions and data loss through heartbeat detection and data integrity checks. Thirdly, real-time status detection is performed on the sensor health status vector set to obtain a sensor fault type code set. Therefore, sensor anomalies can be categorized into three types: communication interruption, data drift, and data loss. This provides a basis for matching differentiated compensation algorithms to each fault type, avoiding compensation mismatch caused by applying the same treatment method to all faults. Fourth, in response to the aforementioned sensor fault type code being a communication interruption code, an autoregressive time series prediction is performed on the initial multiphysics environmental parameter set to obtain the first compensation parameter. Thus, historical data sequences prior to the sensor communication interruption can be used to predict the parameter values ​​at the current moment by analyzing their autocorrelation structure, filling the real-time data gaps caused by the communication interruption and ensuring that the system can still obtain reasonable environmental parameter estimates before communication is restored.Fifth, in response to the aforementioned sensor fault type code being a data drift code, adaptive state correction is performed on the initial multiphysics environmental parameter set to obtain the second compensation parameter. Thus, a Kalman filter can be used to fuse historical state predictions and current observations, and the observation noise covariance matrix can be dynamically adjusted according to the severity of data drift. When sensor readings experience slow drift or abnormal jumps, the weight of unreliable observations is automatically reduced, and a corrected state estimate is output, eliminating the impact of drift on data quality. Sixth, in response to the aforementioned sensor fault type code being a data missing code, physical coupling parameter simulation is performed on the initial multiphysics environmental parameter set to obtain the third compensation parameter. Thus, the known physical correlations between temperature, humidity, air pressure, and VOC concentration can be used to deduce the values ​​of missing parameters from other normal parameters through multiple linear regression, achieving cross-parameter compensation without relying on additional hardware. Seventh, based on the aforementioned first compensation parameter, second compensation parameter, and third compensation parameter, the initial multiphysics environmental parameter set is corrected to obtain the corrected multiphysics environmental parameter set. Therefore, the compensation parameters generated by the three compensation algorithms can accurately replace the corresponding abnormal or missing data, restoring the integrity and consistency of the multiphysics environmental parameter set, and providing complete and reliable input data for subsequent solidification degree prediction and multi-constraint dynamic parameter adjustment. Eighth, the above-mentioned modified multiphysics environmental parameter set is subjected to a rationality check, and the check result is considered passed, thus determining the above-mentioned modified multiphysics environmental parameter set as the multiphysics environmental parameter set. Therefore, by comparing the compensated parameter values ​​with a preset reasonable range, unreasonable estimates caused by compensation algorithm failure or extreme operating conditions can be filtered out, ensuring that the environmental parameter data flowing into the subsequent calculation process has basic physical reliability and preventing erroneous data from causing misjudgments or misoperations. Finally, combined with "Step 105", a fully automated processing chain from raw data acquisition, fault detection and classification, differentiated compensation, rationality check to equipment control can be performed, achieving the effect of avoiding control system interruptions caused by communication interruptions, data drift, or data loss.

[0035] Step 102: Based on the biological clean space, determine the special sealing coating material, and query the material constraint properties of the special sealing coating material to obtain the environmental threshold set.

[0036] In some embodiments, the aforementioned implementing entity may determine a special sealing coating material based on the aforementioned biological clean space, and perform material constraint attribute queries on the aforementioned special sealing coating material to obtain an environmental threshold set. The environmental threshold set may include a temperature threshold range, a humidity threshold upper limit, a pressure gradient threshold range, and a volatile organic compound safety threshold. The aforementioned special sealing coating material may be any one of the following: a solvent-free epoxy sealing coating or a polyurethane antibacterial sealing coating.

[0037] In some optional implementations of certain embodiments, the aforementioned execution entity may, through the following steps, determine a special sealing coating material based on the aforementioned biological clean space, and query the material constraint properties of the aforementioned special sealing coating material to obtain an environmental threshold set: The first step is to use the construction area code of the aforementioned bio-clean space as an index to query the construction work order table to determine the special sealing coating material. The construction work order table may contain the following fields: construction area code (VARCHAR type, primary key), special sealing coating material (VARCHAR type, such as "solvent-free epoxy sealing coating" or "polyurethane antibacterial sealing coating"), coating curing start time (DATETIME type), coating curing end time (DATETIME type), and construction status (VARCHAR type, values ​​include "not started", "in progress", and "completed"). As an example, a record in the above construction work order table can be represented as: {“Construction Area Code”: “BSL3_LAB_A01_WALL”, “Special Sealing Coating Material”: “Solvent-Free Epoxy Sealing Coating”, “Coating Curing Start Time”: “2026-07-27 08:00:00”, “Coating Curing End Time”: “2026-07-28 18:00:00”, “Construction Status”: “In Progress”}.

[0038] The second step involves using the aforementioned special sealing coating material as an index to query the environmental threshold set in the material property table. This material property table includes the environmental threshold sets calibrated by various materials through factory constant temperature and humidity curing tests. For example, a record in the material property table can be represented as: {“Material Name”: “Solvent-Free Epoxy Sealing Coating”, “Lower Temperature Threshold”: 5, “Upper Temperature Threshold”: 35, “Upper Humidity Threshold”: 80, “Lower Pressure Gradient Threshold”: -30, “Upper Pressure Gradient Threshold”: 30, “Volatile Organic Compound Safety Threshold”: 500}.

[0039] Step 103: Based on the multiphysics environmental parameter set and the cumulative time after coating construction, determine the predicted initial curing time, and based on the volatile organic compound concentration value and the volatile organic compound safety threshold, perform a hindrance correction on the predicted initial curing time to obtain the corrected predicted curing time.

[0040] In some embodiments, the execution entity may determine the initial curing time prediction value based on the multiphysics environmental parameter set and the cumulative time after coating construction, and perform a hindrance correction on the initial curing time prediction value based on the volatile organic compound concentration value and the volatile organic compound safety threshold to obtain a corrected curing time prediction value.

[0041] In some optional implementations of certain embodiments, the execution entity may determine the initial curing time prediction value based on the multiphysics environmental parameter set and the cumulative time after coating application, and perform a hindrance correction on the initial curing time prediction value based on the volatile organic compound concentration value and the volatile organic compound safety threshold to obtain a corrected curing time prediction value: The first step is to extract the temperature, humidity, and pressure gradient values ​​of the target timestamp from the aforementioned multiphysics environmental parameter set as real-time status parameters. For example, the target timestamp could be a specific moment after the coating application is completed. For instance, the target timestamp could be "2026-07-27 14:00:00". The real-time status parameters can be represented as {"Real-time temperature": 15.0, "Real-time humidity": 75.0, "Real-time pressure gradient": -5.0}.

[0042] The second step involves obtaining the timestamp of the biological cleanroom at the time of coating completion, and determining the cumulative time after coating completion based on the timestamp and the target timestamp. In practice, the executing entity reads the "coating curing start time" from the work order table as the timestamp of the biological cleanroom at the time of coating completion. The difference between the target timestamp and the timestamp of the biological cleanroom at the time of coating completion is then determined as the cumulative time after coating completion. For example, the timestamp of the biological cleanroom at the time of coating completion could be "2026-07-27 08:00:00". The target timestamp could be "2026-07-27 14:00:00". The cumulative time could be 6 hours.

[0043] The third step involves retrieving the curing kinetic reference parameters from the material environmental constraint parameter table, using the aforementioned special sealing coating material as an index. This table can be a data table recording the curing kinetic parameters of various special sealing coating materials under different environmental conditions. The material environmental constraint parameter table may contain the following fields: material name (VARCHAR type, primary key), reference temperature value (FLOAT type, unit °C), reference humidity value (FLOAT type, unit %RH), reference pressure gradient value (FLOAT type, unit Pa), reference curing time (FLOAT type, unit hour), temperature sensitivity coefficient (FLOAT type, unit 1 / °C), humidity sensitivity coefficient (FLOAT type, unit 1 / %RH), and pressure sensitivity coefficient (FLOAT type, unit 1 / Pa). The aforementioned curing kinetic reference parameters include reference temperature value, reference humidity value, reference pressure gradient value, reference curing time, temperature sensitivity coefficient, humidity sensitivity coefficient, and pressure sensitivity coefficient. The aforementioned curing kinetic baseline parameters were calibrated through constant temperature and humidity curing tests conducted by the material supplier before shipment. The coating material samples were placed in an environmental test chamber with precisely controlled temperature, humidity, and air pressure. Curing tests were conducted under different combinations of environmental parameters, and the curing completion time was recorded. Sensitivity coefficients and baseline values ​​were obtained through multiple linear regression fitting. For example, the aforementioned curing kinetic baseline parameters can be expressed as {"Baseline Temperature": 25, "Baseline Humidity": 60, "Baseline Air Pressure Gradient": 0, "Baseline Curing Time": 48, "Temperature Sensitivity Coefficient": 0.05, "Humidity Sensitivity Coefficient": 0.02, "Air Pressure Sensitivity Coefficient": 0.01}.

[0044] The fourth step involves generating a predicted initial curing time based on the aforementioned real-time state parameters, accumulated time, and curing kinetic baseline parameters. In practice, the executing entity can input the aforementioned real-time state parameters, accumulated time, and curing kinetic baseline parameters into a curing degree mapping rule to obtain the predicted initial curing time. The curing degree mapping rule describes the acceleration or deceleration effect on the curing rate when the real-time state parameters deviate from the curing kinetic baseline parameters. For example, the curing degree mapping rule can be expressed as: Predicted initial curing time = Baseline curing time × (1 + Temperature sensitivity coefficient × (Baseline temperature value - Real-time temperature value) + Humidity sensitivity coefficient × (Real-time humidity value - Baseline humidity value) + Pressure sensitivity coefficient × (Real-time pressure gradient value - Baseline pressure gradient value)) - Accumulated time. Since the aforementioned special sealing coating material is a "solvent-free epoxy sealing coating," the aforementioned baseline curing time can be 48 hours. The predicted initial curing time is calculated as follows: 48 × (1 + 0.05 × (25 - 15) + 0.02 × (75 - 60) + 0.01 × (-5 - 0)) = 48 × (1 + 0.5 + 0.3 - 0.05) = 48 × 1.75 - 6 = 78 hours. This predicted initial curing time can be the time from the target timestamp to complete curing.

[0045] The fifth step is to extract the volatile organic compound concentration values ​​of the target timestamp from the above multiphysics environmental parameter set.

[0046] Step 6: In response to the volatile organic compound (VOC) concentration value being not less than the VOC safety threshold, the initial curing time prediction value is modified by applying a hindrance correction to obtain a modified curing time prediction value. In practice, the executing entity can determine the modified curing time prediction value by dividing the initial curing time prediction value by a preset hindrance coefficient in response to the VOC concentration value being not less than the VOC safety threshold. The preset hindrance coefficient is a pre-calibrated constant with a value ranging from 0.7 to 0.95, and its specific value is determined based on the chemical properties of the special sealing coating material. The preset hindrance coefficient is calibrated as follows: In a constant temperature and humidity test chamber, coating curing tests are conducted under different VOC concentration conditions, the curing completion time is recorded, the ratio of the curing time under high VOC concentration conditions to the curing time under standard conditions is calculated, and the average value of multiple tests is taken as the preset hindrance coefficient. As an example, for solvent-free epoxy sealing coatings, the preset resistance coefficient is 0.9; for polyurethane antibacterial sealing coatings, the preset resistance coefficient is 0.85.

[0047] Step 104: Based on the corrected curing time prediction value, the multi-physics field environmental parameter set and the environmental threshold set, perform multi-constraint dynamic parameter adjustment to obtain the equipment control parameter set.

[0048] In some embodiments, the execution entity may perform multi-constraint dynamic parameter adjustment based on the predicted value of the corrected curing time, the multi-physics environmental parameter set, and the environmental threshold set to obtain a set of equipment control parameters. The set of equipment control parameters includes a sequence of dynamic balance values ​​for airflow, a sequence of temperature control power, a sequence of dehumidification power, and a sequence of volatile organic compound purification power.

[0049] In addressing the technical problems mentioned in the background section, and specifically for the application scenario of special coating construction in biosafety clean spaces (such as biosafety level 3 and above laboratories, vaccine raw material production workshops, and aseptic preparation filling workshops), particularly in large-scale biopharmaceutical bases or P3 / P4 laboratory construction projects involving multiple shifts and parallel construction in multiple areas, the following technical issues often arise: strong coupling effects between multi-physics field control devices lead to repeated oscillations in environmental parameters, and fixed environmental thresholds cannot adapt to different stages of the coating curing process, resulting in low control accuracy, energy waste, and coating quality risks. Considering the following requirements for this application scenario—extremely high environmental parameter stability, complex multi-physics field coupling relationships, and strong sensor fault tolerance—we have decided to adopt the following solution: In some optional implementations of certain embodiments, the aforementioned execution entity may, based on the aforementioned corrected solidification duration prediction value, the aforementioned multi-physics environmental parameter set, and the aforementioned environmental threshold set, perform multi-constraint dynamic parameter adjustment to obtain the equipment control parameter set through the following steps: The first step is to extract the temperature, humidity, pressure gradient, and volatile organic compound (VOC) concentration values ​​of the target timestamp from the aforementioned multiphysics environmental parameter set, and use these as the target multiphysics state vector. For example, the target multiphysics state vector can be represented as {"Temperature": 15.0, "Humidity": 75.0, "Pressure Gradient": -5.0, "VOC Concentration": 350}.

[0050] The second step is to read the cross-coupling coefficient set from the cross-coupling coefficient table. This table is a pre-calibrated two-dimensional lookup table, with row indices representing the special sealing coating material, column indices representing the coupling coefficient type, and table entries representing dimensionless cross-coupling coefficients. The cross-coupling coefficient set includes the first coupling coefficient for airflow change on temperature change, the second coupling coefficient for airflow change on humidity change, the third coupling coefficient for airflow change on volatile organic compound (VOC) concentration change, the fourth coupling coefficient for temperature change on humidity change, and the fifth coupling coefficient for temperature change on VOC concentration change. For example, for a "solvent-free epoxy sealing coating," the cross-coupling coefficient set can be represented as {"first coupling coefficient": -0.3, "second coupling coefficient": -0.5, "third coupling coefficient": -0.8, "fourth coupling coefficient": -0.4, "fifth coupling coefficient": 0.2}. The coupling coefficients were calibrated as follows: In the biological clean space, the output of each control device was adjusted individually, the changes in other physical field parameters were recorded, and the values ​​of each coupling coefficient were obtained by fitting multiple linear regression.

[0051] The third step involves adjusting the environmental threshold set to a tight constraint based on the predicted modified curing time, resulting in a tightly constrained environmental threshold set. In practice, the implementing entity can determine the ratio of the predicted modified curing time to the baseline curing time as the tight constraint ratio factor. Then, using the tight constraint ratio factor as an index, the corresponding tightening ratio is retrieved from the tight constraint coefficient table. Next, the product of the upper limit of the temperature threshold range in the environmental threshold set and the tightening ratio is determined as the tight constraint upper temperature limit; the ratio of the lower limit of the temperature threshold range to the tightening ratio is determined as the tight constraint lower temperature limit; the product of the upper limit of the humidity threshold and the tightening ratio is determined as the tight constraint upper humidity limit; the product of the upper limit of the pressure gradient threshold range and the tightening ratio is determined as the tight constraint upper pressure gradient limit; the ratio of the lower limit of the pressure gradient threshold range to the tightening ratio is determined as the tight constraint lower pressure gradient limit; and the product of the volatile organic compound safety threshold and the tightening ratio is determined as the tight constraint volatile organic compound safety threshold. Finally, the aforementioned upper limit of the confined temperature, the lower limit of the confined temperature, the upper limit of the confined humidity, the upper limit of the confined pressure gradient, the lower limit of the confined pressure gradient, and the safety threshold for volatile organic compounds (VOCs) under confined conditions are determined as the set of confined environmental thresholds. The confined coefficient table can be a pre-calibrated one-dimensional lookup table, with row indices representing confined proportional factors and table entries representing dimensionless tightening ratios. The confined coefficient table can be calibrated as follows: In a biological cleanroom, for each special sealing coating material, in addition to the factory constant temperature and humidity curing test, multiple curing tests under different combinations of environmental parameters are conducted. The specific steps are as follows: First, the coating material sample is placed in an environmental test chamber where temperature, humidity, air pressure, and VOC concentration can be precisely controlled. A baseline curing test is conducted under standard environmental conditions (i.e., baseline temperature, baseline humidity, and baseline air pressure gradient), and the baseline curing time is recorded. Then, curing tests were conducted at multiple gradients deviating from standard environmental conditions (e.g., temperature deviations of ±5℃, ±10℃; humidity deviations of ±10%RH, ±20%RH, etc.), and the actual curing time of each test group was recorded. The ratio of the actual curing time to the baseline curing time was determined as the tight constraint scaling factor.

[0052] The fourth step involves determining the control sequence set based on the aforementioned target multiphysics state vector, the aforementioned cross-coupling coefficient set, and the aforementioned tightly constrained environment threshold set, using a sequential quadratic programming algorithm. In practice, the executing entity can start with the aforementioned target multiphysics state vector, using each cross-coupling coefficient in the aforementioned cross-coupling coefficient set as the off-diagonal element of the state transition matrix. Within a preset control time domain length, the sequential quadratic programming algorithm iteratively solves for the control sequence that minimizes the overall cost, thus obtaining the control sequence set. The preset control time domain length can include ten control cycles. One control cycle can be 30 seconds.

[0053] The aforementioned comprehensive cost is the weighted sum of the squared deviations of each physical field parameter from the aforementioned tightly constrained environmental threshold set under the predicted state and the squared energy consumption of each control variable. Specifically, for each control cycle within the aforementioned preset control time domain length, the aforementioned execution entity performs the following operations: First, it reads the airflow adjustment, temperature control power value, dehumidification power value, and volatile organic compound purification power value from the equipment control parameter set of the previous control cycle, as the current control variable set for the current control cycle. As an example, the current control variable set for the first control cycle can be the initial airflow adjustment, initial temperature control power value, initial dehumidification power value, and initial volatile organic compound purification power value. The aforementioned initial airflow adjustment can be 0 m³ / h. The aforementioned initial temperature control power value can be 0 W. The aforementioned initial dehumidification power value can be 0 W. The aforementioned initial volatile organic compound purification power value can be 0 W. Then, the product of the current control cycle's airflow adjustment amount and the aforementioned first coupling coefficient is determined as the predicted change in temperature due to airflow; the product of the temperature control power value and the aforementioned fourth coupling coefficient is determined as the predicted change in humidity due to temperature; the product of the airflow adjustment amount and the aforementioned second coupling coefficient is determined as the predicted change in humidity due to airflow; the product of the airflow adjustment amount and the aforementioned third coupling coefficient is determined as the predicted change in VOC concentration due to airflow; and the product of the temperature control power value and the aforementioned fifth coupling coefficient is determined as the predicted change in VOC concentration due to temperature. The product of the temperature control power value and the temperature control efficiency coefficient is determined as the influence of temperature control power on temperature. For example, the aforementioned temperature control efficiency coefficient can be 0.8℃ / kW. The product of the dehumidification power value and the dehumidification efficiency coefficient is determined as the influence of dehumidification power on temperature. For example, the aforementioned dehumidification efficiency coefficient can be 1.5%RH / kW. The product of the volatile organic compound purification power value and the purification efficiency coefficient is determined as the influence of volatile organic compound purification power on volatile organic compound concentration. For example, the purification efficiency coefficient mentioned above can be 200 ppm / kW. The temperature value of the current control cycle, the predicted change in temperature due to airflow, and the influence of temperature control power on temperature are summed to determine the temperature value of the next control cycle; the humidity value of the current control cycle, the predicted change in humidity due to airflow, the predicted change in humidity due to temperature, and the influence of dehumidification power on temperature are summed to determine the humidity value of the next control cycle; the air pressure gradient value of the current control cycle is added to the airflow adjustment amount (airflow changes directly affect the air pressure gradient) to obtain the air pressure gradient value of the next control cycle; the volatile organic compound (VOC) concentration value of the current control cycle, the predicted change in VOC concentration due to airflow, the predicted change in VOC concentration due to temperature, and the influence of VOC purification power on VOC concentration are summed to determine the VOC concentration value of the next control cycle.The predicted state vector is obtained by combining the temperature, humidity, pressure gradient, and volatile organic compound (VOC) concentration values ​​for the next control cycle. Then, the differences between each parameter in the predicted state vector and the corresponding threshold in the tightly constrained environment threshold set are determined to obtain the temperature deviation, humidity deviation, pressure gradient deviation, and VOC deviation values. Next, each deviation value is squared, multiplied by its corresponding deviation weighting coefficient, and summed to obtain the deviation cost component. Simultaneously, the airflow adjustment, temperature control power, dehumidification power, and VOC purification power values ​​in the current control variable set for the current control cycle are squared, multiplied by their corresponding energy consumption weighting coefficients, and summed to obtain the energy consumption cost component. Finally, the deviation cost components and energy consumption cost components for all control cycles within the preset control time domain are summed to obtain the comprehensive cost. For example, the deviation weighting coefficient for the temperature deviation value can be 2.0. The deviation weighting coefficient for the humidity deviation value can also be 2.0. The deviation weighting coefficient corresponding to the air pressure gradient deviation value can be 1.0. The deviation weighting coefficient corresponding to the volatile organic compound deviation value can be 1.5. The energy consumption weighting coefficient corresponding to the above air volume adjustment value can be 0.3. The energy consumption weighting coefficient corresponding to the above temperature control power value can be 0.5. The energy consumption weighting coefficient corresponding to the above dehumidification power value can be 0.4. The energy consumption weighting coefficient corresponding to the above volatile organic compound purification power value can be 0.2.

[0054] The aforementioned Sequential Quadratic Programming (SQP) algorithm can be a nonlinear optimization algorithm. Specifically, in this implementation, the algorithm's execution process is as follows: First, starting with the aforementioned target multiphysics state vector, and using each cross-coupling coefficient in the aforementioned cross-coupling coefficient set as the off-diagonal element of the state transition matrix, the first-order partial derivative vector and second-order partial derivative matrix of the aforementioned comprehensive cost relative to the aforementioned current control variable set are determined, resulting in the gradient vector and Hessian matrix. The aforementioned gradient vector and Hessian matrix are used as the coefficients of the quadratic programming subproblem, and the aforementioned tightly constrained environment threshold set is used as the linear inequality constraint boundary of the quadratic programming subproblem, constructing the quadratic programming subproblem data volume. The aforementioned quadratic programming subproblem data volume includes the quadratic term coefficient matrix, the linear term coefficient vector, and the linear constraint matrix of the objective function. Second, the quadratic programming solver is invoked, using the aforementioned quadratic programming subproblem data volume as input, to obtain the search direction vector. The aforementioned search direction vector includes the search direction vectors for airflow regulation, temperature control power, dehumidification power, and volatile organic compound purification power. Third, select step sizes from the set of step sizes, and multiply the current control variable set by the search direction vector and each step size to obtain each updated control variable set. Determine the comprehensive cost of each updated control variable set, and select the step size that minimizes the comprehensive cost as the current step size. Multiply the current control variable set by the search direction vector and the current step size to obtain the target control variable set. Fourth, determine the absolute value of the difference between the comprehensive cost of the target control variable set and the comprehensive cost of the previous iteration. If the absolute value of the difference is less than a preset convergence threshold, stop the iteration, and determine the target control variable set as the optimal control variable set. Fifth, arrange the airflow regulation, temperature control power, dehumidification power, and volatile organic compound purification power values ​​in the optimal control variable set according to the control cycle order to obtain the airflow regulation sequence, temperature control power sequence, dehumidification power sequence, and volatile organic compound purification power sequence. The aforementioned airflow regulation sequence, temperature control power sequence, dehumidification power sequence, and volatile organic compound purification power sequence are defined as the control sequence set. As an example, the aforementioned step size set can be {0.5, 0.25, 0.125, 0.0625, 0.03125}. The aforementioned quadratic programming solver can be an interior-point solver or an effective set solver. The aforementioned preset convergence threshold can be 0.001.

[0055] The fifth step involves power correction of the aforementioned control sequence set to obtain a corrected control sequence set. In practice, the executing entity can perform the following power correction operation on each control sequence in the control sequence set: compare the value of each control quantity in the control sequence with the rated power limit of the corresponding device; if the value of the control quantity exceeds the rated power limit, truncate the value to the rated power limit; if the value of the control quantity is negative, set it to zero. Simultaneously, look up the predicted value of the corrected curing time from the power correction coefficient table to obtain the power correction coefficient. Then, the product of the power correction coefficient and each control quantity value is used to determine each corrected control quantity value. Afterward, arrange the corrected control quantity values ​​in order of control cycle to obtain the corrected control sequence. Finally, determine the corrected control sequence set. The power correction coefficient table can be a pre-calibrated one-dimensional lookup table, with row indices representing the predicted corrected curing time values ​​and table entries representing dimensionless power correction coefficients. The aforementioned set of calibration control sequences includes a calibration airflow regulation sequence, a calibration temperature control power sequence, a calibration dehumidification power sequence, and a calibration volatile organic compound purification power sequence.

[0056] Step 6: Based on the pressure gradient values ​​of the aforementioned multiphysics environmental parameter set, the aforementioned tight-constraint environmental threshold set, and the aforementioned corrected airflow adjustment sequence in the aforementioned corrected control sequence set, a dynamic balance value sequence for airflow is generated. In practice, the executing entity can determine the target pressure gradient value as the average of the upper and lower limits of the tight-constraint pressure gradient. Then, using the difference between the target pressure gradient value and the pressure gradient values ​​in the aforementioned multiphysics environmental parameter set as the deviation input, and the corrected airflow adjustment amount of the first control cycle in the aforementioned corrected airflow adjustment sequence as the feedforward input, an incremental PID (Proportional-Integral-Derivative) controller is used to generate the dynamic balance value sequence for airflow. The incremental PID controller can output the airflow adjustment increment of the current control cycle relative to the previous control cycle, and add the airflow adjustment increment to the airflow adjustment amount of the previous control cycle to obtain the dynamic balance value for the current control cycle. The dynamic balance values ​​for each control cycle are arranged in chronological order to obtain the dynamic balance value sequence for airflow.

[0057] Step 7: Combine the above-mentioned dynamic balance value sequence of air volume, the above-mentioned temperature control power sequence, the above-mentioned dehumidification power sequence, and the above-mentioned volatile organic compound purification power sequence into a set of equipment control parameters.

[0058] The above-mentioned technical content and related content, as an inventive point of this disclosure, combined with "step 105," solves the technical problem that "strong coupling effects between multi-physics field control devices lead to repeated oscillations in environmental parameters, and fixed environmental thresholds cannot adapt to different stages of coating curing, resulting in low control accuracy, energy waste, and coating quality risks." The factors leading to low control accuracy, energy waste, and coating quality risks are often as follows: In the prior art, ventilation, temperature control, dehumidification, and volatile organic compound (VOC) purification devices receive control commands independently, without considering the cross-coupling effects of airflow changes on temperature, humidity, and VOC concentration, or the coupling effects of temperature changes on humidity and VOC concentration, resulting in overshoot and repeated oscillations of environmental parameters during the adjustment process. Simultaneously, fixed environmental thresholds cannot dynamically adjust constraint boundaries according to the coating curing process. Too loose constraints in the early stages of curing may lead to substandard environmental conditions, while too tight constraints in the later stages may result in unnecessary equipment energy consumption. Solving these factors enables collaborative optimization control in multi-device coupled scenarios, avoiding environmental parameter oscillations and dynamically adjusting constraint boundaries according to the curing process, thereby reducing energy consumption while ensuring coating quality. To achieve this effect, firstly, the temperature, humidity, pressure gradient, and volatile organic compound (VOC) concentration values ​​of the target timestamp are extracted from the aforementioned multiphysics environmental parameter set and used as the target multiphysics state vector. This allows multidimensional environmental parameters to be integrated into a structured state representation, providing unified input data for subsequent coupled modeling and optimized control. Secondly, the cross-coupling coefficient set is read from the cross-coupling coefficient table. This allows for the acquisition of quantitative coupling relationships between airflow, temperature, humidity, and VOC concentration, incorporating previously isolated equipment control into a unified coupling model and providing a mathematical basis for eliminating mutual interference between equipment. Thirdly, based on the aforementioned corrected curing time prediction value, the aforementioned environmental threshold set is adjusted with tight constraints to obtain a tightly constrained environmental threshold set. This allows for dynamic tightening or relaxation of environmental constraint boundaries based on the actual progress of coating curing, maintaining strict constraints in the early stages of curing to ensure coating quality, and appropriately relaxing constraints in the later stages of curing to reduce energy consumption, achieving a dynamic balance between process objectives and energy-saving objectives. Fourthly, based on the aforementioned target multiphysics state vector, the aforementioned cross-coupling coefficient set, and the aforementioned tightly constrained environmental threshold set, a sequential quadratic programming algorithm is used to determine the control sequence set. Therefore, considering the coupling effect of the equipment, global optimization can be performed over multiple preset future control cycles to output a set of control sequences that minimize the weighted sum of environmental deviation and energy consumption, fundamentally avoiding the oscillation problem caused by independent adjustment in a single cycle. Fifth, power correction is performed on the above control sequence set to obtain a corrected control sequence set. This allows the optimized output control quantity to be limited within the rated power range of the equipment, and the control quantity can be scaled and adjusted according to the solidification progress, ensuring that the control commands are executed within the physically feasible range and avoiding equipment overload or invalid output.Sixth, based on the pressure gradient values ​​of the aforementioned multiphysics environmental parameter set, the aforementioned tight-constraint environmental threshold set, and the aforementioned corrected airflow adjustment sequence in the aforementioned corrected control sequence set, an incremental PID controller is used to generate a dynamic balance value sequence for airflow. This allows the optimized open-loop airflow adjustment to be combined with the closed-loop feedback control of the pressure gradient, using the PID controller to eliminate model errors and external disturbances, achieving precise and stable control of the pressure gradient. Seventh, the aforementioned dynamic balance value sequence for airflow, the aforementioned temperature control power sequence, the aforementioned dehumidification power sequence, and the aforementioned volatile organic compound purification power sequence are merged into a set of equipment control parameters. This allows the control commands for the four types of equipment to be aligned along the same time axis, forming a complete control scheme that can be issued at once, ensuring that each piece of equipment operates collaboratively within the same control cycle and avoiding control conflicts caused by disordered command timing. Finally, by combining "Step 105", a complete control process is carried out, from multi-physics coupling modeling, dynamic threshold adjustment, global optimization solution, power correction, closed-loop compensation to equipment control. This process can achieve collaborative optimization control in multi-device coupling scenarios, avoid environmental parameter oscillations, and dynamically adjust constraint boundaries according to the curing process, thereby reducing energy consumption while ensuring coating quality.

[0059] Step 105: Send the set of equipment control parameters to the multiphysics control device to control the temperature, humidity, air pressure gradient and volatile organic compound concentration of the biological clean space.

[0060] In some embodiments, the aforementioned executing entity may send the aforementioned set of device control parameters to a multi-physics control device to control the temperature, humidity, air pressure gradient, and volatile organic compound concentration of the aforementioned biological clean space. The aforementioned multi-physics control device may include ventilation control equipment, temperature control equipment, humidity control equipment, and volatile organic compound purification equipment.

[0061] In practice, the aforementioned executing entity can send the aforementioned dynamic airflow balance command to the aforementioned ventilation control equipment, the aforementioned temperature control output power command to the aforementioned temperature control equipment, the aforementioned dehumidification control command to the aforementioned humidity control equipment, and the aforementioned volatile organic compound (VOC) purification command to the aforementioned VOC purification equipment. The aforementioned ventilation control equipment can be electromechanical equipment used to regulate airflow and pressure gradient within the biological clean space. For example, the aforementioned ventilation control equipment can be a centrifugal exhaust fan of model "YWF4D-500," equipped with an ABB ACS580 series frequency converter, receiving the dynamic airflow balance command via the Modbus RTU protocol. The aforementioned temperature control equipment can be electromechanical equipment used to raise or lower the temperature within the biological clean space. For example, the aforementioned temperature control equipment can be an electric heater of model "DB-2000," with a rated power of 2000W, receiving the temperature control output power command via an RS485 interface. The aforementioned humidity control equipment can be electromechanical equipment used to lower the relative humidity within the biological clean space. As an example, the humidity control device mentioned above could be an industrial dehumidifier, model "DH-858D," with a dehumidification capacity of 58L / day, receiving dehumidification control commands via WiFi. The volatile organic compound (VOC) purification device mentioned above could be a purification device used to remove VOCs from biological clean spaces. As an example, the VOC purification device mentioned above could be a photocatalytic oxidation purifier, model "HC-1000," with a processing air volume of 1000m³ / h, receiving VOC purification commands via an RS485 interface.

[0062] The above-described embodiments of this disclosure have the following beneficial effects: Through the multi-physics field linkage control method for the construction of special coatings in biological clean spaces, as described in some embodiments of this disclosure, the methods achieve the following effects: real-time acquisition of multi-physics field environmental parameters, dynamic prediction and hindrance correction of curing time, adjustment of multiple constraint dynamic parameters, and collaborative control of multiple devices. These methods avoid quality defects such as incomplete or over-curing of the coating, eliminate the phenomenon of equipment response lagging behind environmental changes, and improve the system's fault tolerance in sensor failure scenarios. Specifically, the reason for incomplete or over-curing of the coating, leading to sealing failure, microbial penetration, and other quality defects, is that the curing process of special sealing coatings is highly sensitive to temperature, humidity, air pressure, and the concentration of volatile organic compounds. The curing time, curing conditions, and other process parameters in existing construction technical disclosure documents are fixed values ​​measured under standard environmental conditions at the time of manufacture, and cannot be dynamically calibrated according to the actual temperature, humidity, air pressure gradient, and volatile organic compound concentration at the construction site. When the actual environmental conditions deviate from the standard conditions, if construction personnel still operate according to the fixed process parameters, incomplete or over-curing of the coating will occur, leading to sealing failure, microbial penetration, and other quality defects. Based on this, the multi-physics linkage control method for special coating construction in biological clean spaces, as disclosed in some embodiments, firstly collects a set of multi-physics environmental parameters according to a preset sampling period through an Internet of Things (IoT) sensor network deployed in the biological clean space. This establishes a real-time data channel from the physical environment to the digital system, converting changes in temperature, humidity, air pressure gradient, and VOC concentration into a continuous data stream that can be processed by a computer, providing real-time and accurate input data for subsequent curing time prediction and multi-constraint dynamic parameter adjustment. Secondly, based on the aforementioned biological clean space, a special sealing coating material is determined, and its material constraint properties are queried to obtain an environmental threshold set. This allows for precise association between the current construction area and the specific coating material used, ensuring that subsequent threshold retrieval and parameter calculation target the correct material type, avoiding calculation errors caused by material confusion, and simultaneously obtaining the environmental parameter boundaries that allow construction with the material, providing a clear judgment standard for environmental compliance determination. Then, based on the aforementioned multiphysics environmental parameter set and the cumulative time after coating application, the predicted initial curing time is determined. Furthermore, based on the aforementioned volatile organic compound (VOC) concentration and VOC safety threshold, a hindrance correction is applied to the predicted initial curing time to obtain the corrected predicted curing time. Therefore, the remaining curing time required for the coating can be dynamically calculated based on real-time environmental parameters, ensuring that the process parameters in the construction technical briefing are matched with actual environmental conditions in real time. It also automatically extends the curing time when the VOC concentration exceeds the standard, avoiding incomplete curing due to unfavorable environmental conditions.Then, based on the aforementioned corrected curing time prediction, the aforementioned multiphysics environmental parameter set, and the aforementioned environmental threshold set, multi-constraint dynamic parameter adjustment is performed to obtain the equipment control parameter set. Thus, considering the cross-coupling effect between airflow, temperature, humidity, and VOC concentration, the environmental constraint boundaries can be dynamically adjusted according to the curing process. A global optimization algorithm is used to solve for the control sequence that minimizes the weighted sum of environmental deviation and energy consumption within several preset future control cycles, achieving coordinated control of multiple devices and fundamentally avoiding the oscillation problems and energy waste caused by single-cycle independent adjustment. Finally, the aforementioned equipment control parameter set is sent to the multiphysics control device to control the temperature, humidity, air pressure gradient, and volatile organic compound concentration of the aforementioned biological clean space. Thus, the optimized control commands can be accurately issued to each execution device, realizing a complete closed loop from environmental perception and dynamic calculation of process parameters to automatic equipment control. This implementation method achieves the technical effects of avoiding quality defects such as incomplete or over-cured coatings, eliminating the phenomenon of equipment response lagging behind environmental changes, and improving the system's fault tolerance in sensor failure scenarios.

[0063] Continue to refer to Figure 2 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of a multi-physics linkage control device for the construction of special coatings in biological clean spaces. These device embodiments are similar to... Figure 1 Corresponding to the method embodiments shown, this multi-physics linkage control device for the construction of special coatings in biological clean spaces can be specifically applied to various electronic devices.

[0064] like Figure 2As shown, a multi-physics linkage control device 200 for the construction of special coatings in biological clean spaces includes: a data acquisition unit 201, a first determination unit 202, a second determination unit 203, an adjustment unit 204, and a transmission unit 205. The data acquisition unit 201 is configured to acquire a set of multi-physics environmental parameters at a preset sampling period via an Internet of Things (IoT) sensor network deployed in the biological clean space. The multi-physics environmental parameters in the set include temperature, humidity, air pressure gradient, and volatile organic compound (VOC) concentration. The first determination unit 202 is configured to determine the special sealing coating material based on the biological clean space and to query the material constraint properties of the special sealing coating material to obtain a set of environmental thresholds. The environmental thresholds include a temperature threshold range, a humidity threshold upper limit, an air pressure gradient threshold range, and a VOC safety threshold. The second determination unit 203 is configured to determine the VOC concentration based on the multi-physics environmental parameter set and the accumulated time after coating construction. An initial curing time prediction value is determined, and based on the aforementioned volatile organic compound (VOC) concentration value and the aforementioned VOC safety threshold, the initial curing time prediction value is modified to obtain a corrected curing time prediction value. The adjustment unit 204 is configured to perform multi-constraint dynamic parameter adjustment based on the corrected curing time prediction value, the aforementioned multi-physics environmental parameter set, and the aforementioned environmental threshold set to obtain an equipment control parameter set. This equipment control parameter set includes a dynamic balance value sequence of airflow, a temperature control power sequence, a dehumidification power sequence, and a VOC purification power sequence. The sending unit 205 is configured to send the equipment control parameter set to a multi-physics control device to control the temperature, humidity, air pressure gradient, and VOC concentration of the aforementioned biological clean space.

[0065] It is understandable that the units described in the multi-physics field linkage control device 200 for the construction of special coatings for biological clean spaces are related to the reference. Figure 1 The steps in the described method correspond accordingly. Therefore, the operations, features, and beneficial effects described above for the method are also applicable to the multi-physics linkage control device 200 and its constituent units for the construction of special coatings for biological clean spaces, and will not be repeated here.

[0066] The following is for reference. Figure 3 It shows a method suitable for implementing this disclosure. Figure 1 A schematic diagram of the structure of an electronic device 300 in some corresponding embodiments. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0067] like Figure 3As shown, the electronic device 300 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory 302 or a program loaded from a storage device 308 into a random access memory 303. The random access memory 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, the read-only memory 302, and the random access memory 303 are interconnected via a bus 304. An input / output interface 305 is also connected to the bus 304.

[0068] Typically, the following devices can be connected to the input / output interface 305: input devices 306 including, for example, a touchscreen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 308 including, for example, magnetic tape, hard disk, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0069] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 309, or installed from a storage device 308, or installed from a read-only memory 302. When the computer program is executed by the processing device 301, it performs the functions defined in the methods of some embodiments of this disclosure.

[0070] It should be noted that, in some embodiments of this disclosure, the computer-readable medium described above may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical fiber, a portable compact disk read-only memory, an optical storage device, a magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0071] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0072] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: collect a set of multi-physics environmental parameters according to a preset sampling period via an Internet of Things (IoT) sensor network deployed in the biological clean space, wherein the multi-physics environmental parameters in the set include temperature, humidity, air pressure gradient, and volatile organic compound (VOC) concentration; determine a special sealing coating material based on the aforementioned biological clean space, and perform material constraint property queries on the aforementioned special sealing coating material to obtain a set of environmental thresholds, wherein the environmental threshold set includes a temperature threshold range, a humidity threshold upper limit, an air pressure gradient threshold range, and a VOC safety threshold; and, based on the aforementioned multi-physics environmental parameters... The cumulative time after the coating application is completed is used to determine the initial curing time prediction. Based on the volatile organic compound (VOC) concentration and the VOC safety threshold, the initial curing time prediction is modified to obtain a corrected curing time prediction. Based on this corrected curing time prediction, the multi-physics environmental parameter set and the environmental threshold set are dynamically adjusted using multiple constraints to obtain an equipment control parameter set. This set includes a dynamic balance value sequence for airflow, a temperature control power sequence, a dehumidification power sequence, and a VOC purification power sequence. This equipment control parameter set is then sent to a multi-physics control device to control the temperature, humidity, air pressure gradient, and VOC concentration in the biological clean space.

[0073] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0074] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0075] The units described in some embodiments of this disclosure can be implemented in software or in hardware. The described units can also be located in a processor.

[0076] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0077] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A multi-physics field linkage control method for the construction of special coatings in biological clean spaces, characterized in that, include: By deploying an Internet of Things (IoT) sensor network in the biological clean space, a set of multi-physics environmental parameters is collected according to a preset sampling period. The multi-physics environmental parameters in the set include temperature, humidity, air pressure gradient, and volatile organic compound concentration. Based on the biological clean space, a special sealing coating material is determined, and the material constraint properties of the special sealing coating material are queried to obtain an environmental threshold set, wherein the environmental threshold set includes a temperature threshold range, a humidity threshold upper limit, an air pressure gradient threshold range, and a volatile organic compound safety threshold. Based on the set of multiphysics environmental parameters and the cumulative time after coating application, the initial curing time prediction is determined, and based on the volatile organic compound concentration and the volatile organic compound safety threshold, the initial curing time prediction is modified to obtain the corrected curing time prediction. Based on the predicted value of the corrected curing time, the multi-physics environmental parameter set and the environmental threshold set are adjusted by multi-constraint dynamic parameters to obtain the equipment control parameter set, wherein the equipment control parameter set includes a dynamic balance value sequence of air volume, a temperature control power sequence, a dehumidification power sequence and a volatile organic compound purification power sequence. The set of device control parameters is sent to a multiphysics control device to control the temperature, humidity, pressure gradient, and volatile organic compound concentration of the biological clean space.

2. The method according to claim 1, characterized in that, The multi-physics field control equipment includes ventilation control equipment, temperature control equipment, humidity control equipment, and volatile organic compound purification equipment.

3. The method according to claim 1, characterized in that, The special sealing coating material is any one of the following: solvent-free epoxy sealing coating or polyurethane antibacterial sealing coating.

4. The method according to claim 1, characterized in that, The method involves using an IoT sensor network deployed in the bio-clean space to collect a set of multi-physics environmental parameters at a preset sampling period, including: The IoT sensor network is controlled to collect data according to a preset sampling period to obtain a raw multiphysics environmental parameter set, wherein the IoT sensor network includes a temperature and humidity sensor, a barometric pressure sensor, and a volatile organic compound sensor. The original multiphysics environment parameter set is filtered for outliers to obtain the new multiphysics environment parameter set.

5. The method according to claim 1, characterized in that, The process of determining a special sealing coating material based on the biological clean space, and querying the material constraint properties of the special sealing coating material to obtain an environmental threshold set, includes: Using the construction area code of the aforementioned biological clean space as an index, the special sealing coating material is determined by querying the construction work order table. Using the special sealing coating material as an index, the environmental threshold set is queried in the material property table, wherein the material property table includes the environmental threshold set calibrated by the factory constant temperature and humidity curing test for various materials.

6. The method according to claim 1, characterized in that, The process of determining the initial curing time prediction value based on the multiphysics environmental parameter set and the cumulative time after coating application, and then applying a hindrance correction to the initial curing time prediction value based on the volatile organic compound concentration value and the volatile organic compound safety threshold to obtain a corrected curing time prediction value, includes: The temperature, humidity and air pressure gradient values ​​of the target timestamp are extracted from the multiphysics environmental parameter set and used as real-time state parameters. Obtain the timestamp of the biological clean space when the coating construction is completed, and determine the cumulative time after the coating construction is completed based on the timestamp and the target timestamp; Using the special sealing coating material as an index, the curing kinetic reference parameters are retrieved from the material environmental constraint parameter table. The curing kinetic reference parameters include reference temperature value, reference humidity value, reference air pressure gradient value, reference curing time, temperature sensitivity coefficient, humidity sensitivity coefficient, and air pressure sensitivity coefficient. Based on the real-time status parameters, the time accumulation, and the curing kinetics baseline parameters, an initial curing time prediction value is generated; Extract the volatile organic compound concentration values ​​of the target timestamp from the multiphysics environmental parameter set; In response to the volatile organic compound concentration value at the target timestamp being not less than the volatile organic compound safety threshold, the initial curing time prediction value is modified by a hindrance correction to obtain a modified curing time prediction value.

7. A multi-physics field linkage control device for the construction of special coatings in biological clean spaces, characterized in that, include: The acquisition unit is configured to acquire a set of multi-physics environmental parameters according to a preset sampling period through an Internet of Things sensor network deployed in the biological clean space. The multi-physics environmental parameters in the set include temperature, humidity, air pressure gradient, and volatile organic compound concentration. The first determining unit is configured to determine a special sealing coating material based on the biological clean space, and to query the material constraint properties of the special sealing coating material to obtain an environmental threshold set, wherein the environmental threshold set includes a temperature threshold range, a humidity threshold upper limit, an air pressure gradient threshold range, and a volatile organic compound safety threshold. The second determining unit is configured to determine the initial curing time prediction value based on the multiphysics environmental parameter set and the cumulative time after the coating construction is completed, and to perform a hindrance correction on the initial curing time prediction value based on the volatile organic compound concentration value and the volatile organic compound safety threshold to obtain a corrected curing time prediction value. The adjustment unit is configured to perform multi-constraint dynamic parameter adjustment based on the corrected curing time prediction value, the multi-physics field environmental parameter set and the environmental threshold set to obtain a set of equipment control parameters, wherein the set of equipment control parameters includes a sequence of air volume dynamic balance values, a sequence of temperature control power, a sequence of dehumidification power and a sequence of volatile organic compound purification power. The transmitting unit is configured to send the set of device control parameters to a multiphysics control device to control the temperature, humidity, pressure gradient, and volatile organic compound concentration of the biological clean space.

8. An electronic device, characterized in that, include: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-6.

9. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-6.

Images